Author Archives: Google AI

Learning to Assemble and to Generalize from Self-Supervised Disassembly



Our physical world is full of different shapes, and learning how they are all interconnected is a natural part of interacting with our surroundings — for example, we understand that coat hangers hook onto clothing racks, power plugs insert into wall outlets, and USB cables fit into USB sockets. This general concept of “how things fit together'' based on their shapes is something that people acquire over time and experience, and it helps to increase the efficiency with which we perform tasks, like assembling DIY furniture kits or packing gifts into a box. If robots could learn “how things fit together,” then perhaps they could become more adaptable to new manipulation tasks involving objects they have never seen before, like reconnecting severed pipes, or building makeshift shelters by piecing together debris during disaster response scenarios.

To explore this idea, we worked with researchers from Stanford and Columbia Universities to develop Form2Fit, a robotic manipulation algorithm that uses deep neural networks to learn to visually recognize how objects correspond (or “fit”) to each other. To test this algorithm, we tasked a real robot to perform kit assembly, where it needed to accurately assemble objects into a blister pack or corrugated display to form a single unit. Previous systems built for this task required extensive manual tuning to assemble a single kit unit at a time. However, we demonstrate that by learning the general concept of “how things fit together,” Form2Fit enables our robot to assemble various types of kits with a 94% success rate. Furthermore, Form2Fit is one of the first systems capable of generalizing to new objects and kitting tasks not seen during training.
Form2Fit learns to assemble a wide variety of kits by finding geometric correspondences between object surfaces and their target placement locations. By leveraging geometric information learned from multiple kits during training, the system generalizes to new objects and kits.
While often overlooked, shape analysis plays an important role in manipulation, especially for tasks like kit assembly. In fact, the shape of an object often matches the shape of its corresponding space in the packaging, and understanding this relationship is what allows people to do this task with minimal guesswork. At its core, Form2Fit aims to learn this relationship by training over numerous pairs of objects and their corresponding placing locations across multiple different kitting tasks – with the goal to acquire a broader understanding of how shapes and surfaces fit together. Form2Fit improves itself over time with minimal human supervision, gathering its own training data by repeatedly disassembling completed kits through trial and error, then time-reversing the disassembly sequences to get assembly trajectories. After training overnight for 12 hours, our robot learns effective pick and place policies for a variety of kits, achieving 94% assembly success rates with objects and kits in varying configurations, and over 86% assembly success rates when handling completely new objects and kits.

Data-Driven Shape Descriptors For Generalizable Assembly
The core component of Form2Fit is a two-stream matching network that learns to infer orientation-sensitive geometric pixel-wise descriptors for objects and their target placement locations from visual data. These descriptors can be understood as compressed 3D point representations that encode object geometry, textures, and contextual task-level knowledge. Form2Fit uses these descriptors to establish correspondences between objects and their target locations (i.e., where they should be placed). Since these descriptors are orientation-sensitive, they allow Form2Fit to infer how the picked object should be rotated before it is placed in its target location.

Form2Fit uses two additional networks to generate valid pick and place candidates. A suction network gets fed a 3D image of the objects and generates pixel-wise predictions of suction success. The suction probability map is visualized as a heatmap, where hotter pixels indicate better locations to grasp the object at the 3D location of the corresponding pixel. In parallel, a place network gets fed a 3D image of the target kit and outputs pixel-wise predictions of placement success. These, too, are visualized as a heatmap, where higher confidence values serve as better locations for the robot arm to approach from a top-down angle to place the object. Finally, the planner integrates the output of all three modules to produce the final pick location, place location and rotation angle.
Overview of Form2Fit. The suction and place networks infer candidate picking and placing locations in the scene respectively. The matching network generates pixel-wise orientation-sensitive descriptors to match picking locations to their corresponding placing locations. The planner then integrates it all to control the robot to execute the next best pick and place action.
Learning Assembly from Disassembly
Neural networks require large amounts of training data, which can be difficult to collect for tasks like assembly. Precisely inserting objects into tight spaces with the correct orientation (e.g., in kits) is challenging to learn through trial and error, because the chances of success from random exploration can be slim. In contrast, disassembling completed units is often easier to learn through trial and error, since there are fewer incorrect ways to remove an object than there are to correctly insert it. We leveraged this difference in order to amass training data for Form2Fit.
An example of self-supervision through time-reversal: rewinding a disassembly sequence of a deodorant kit over time generates a valid assembly sequence.
Our key observation is that in many cases of kit assembly, a disassembly sequence – when reversed over time – becomes a valid assembly sequence. This concept, called time-reversed disassembly, enables Form2Fit to train entirely through self-supervision by randomly picking with trial and error to disassemble a fully-assembled kit, then reversing that disassembly sequence to learn how the kit should be put together.

Generalization Results
The results of our experiments show great potential for learning generalizable policies for assembly. For instance, when a policy is trained to assemble a kit in only one specific position and orientation, it can still robustly assemble random rotations and translations of the kit 90% of the time.
Form2Fit policies are robust to a wide range of rotations and translations of the kits.
We also find that Form2Fit is capable of tackling novel configurations it has not been exposed to during training. For example, when training a policy on two single-object kits (floss and tape), we find that it can successfully assemble new combinations and mixtures of those kits, even though it has never seen such configurations before.
Form2Fit policies can generalize to novel kit configurations such as multiple versions of the same kit and mixtures of different kits.
Furthermore, when given completely novel kits on which it has not been trained, Form2Fit can generalize using its learned shape priors to assemble those kits with over 86% assembly accuracy.
Form2Fit policies can generalize to never-before-seen single and multi-object kits.
What Have the Descriptors Learned?
To explore what the descriptors of the matching network from Form2Fit have learned to encode, we visualize the pixel-wise descriptors of various objects in RGB colorspace through use of an embedding technique called t-SNE.
The t-SNE embedding of the learned object descriptors. Similarly oriented objects of the same category display identical colors (e.g. A, B or F, G) while different objects (e.g. C, H) and same objects but different orientation (e.g. A, C, D or H, F) exhibit different colors.
We observe that the descriptors have learned to encode (a) rotation — objects oriented differently have different descriptors (A, C, D, E) and (H, F); (b) spatial correspondence — same points on the same oriented objects share similar descriptors (A, B) and (F, G); and (c) object identity — zoo animals and fruits exhibit unique descriptors (columns 3 and 4).

Limitations & Future Work
While Form2Fit’s results are promising, its limitations suggest directions for future work. In our experiments, we assume a 2D planar workspace to constrain the kit assembly task so that it can be solved by sequencing top-down picking and placing actions. This may not work for all cases of assembly – for example, when a peg needs to be precisely inserted at a 45 degree angle. It would be interesting to expand Form2Fit to more complex action representations for 3D assembly.

You can learn more about this work and download the code from our GitHub repository.


Acknowledgments
This research was done by Kevin Zakka, Andy Zeng, Johnny Lee, and Shuran Song (faculty at Columbia University), with special thanks to Nick Hynes, Alex Nichol, and Ivan Krasin for fruitful technical discussions; Adrian Wong, Brandon Hurd, Julian Salazar, and Sean Snyder for hardware support; Ryan Hickman for valuable managerial support; and Chad Richards for helpful feedback on writing.

Source: Google AI Blog


On-Device Captioning with Live Caption



Captions for audio content are essential for the deaf and hard of hearing, but they benefit everyone. Watching video without audio is common — whether on the train, in meetings, in bed or when the kids are asleep — and studies have shown that subtitles can increase the duration of time that users spend watching a video by almost 40%. Yet caption support is fragmented across apps and even within them, resulting in a significant amount of audio content that remains inaccessible, including live blogs, podcasts, personal videos, audio messages, social media and others.
Recently we introduced Live Caption, a new Android feature that automatically captions media playing on your phone. The captioning happens in real time, completely on-device, without using network resources, thus preserving privacy and lowering latency. The feature is currently available on Pixel 4 and Pixel 4 XL, will roll out to Pixel 3 models later this year, and will be more widely available on other Android devices soon.
When media is playing, Live Caption can be launched with a single tap from the volume control to display a caption box on the screen.
Building Live Caption for Accuracy and Efficiency
Live Caption works through a combination of three on-device deep learning models: a recurrent neural network (RNN) sequence transduction model for speech recognition (RNN-T), a text-based recurrent neural network model for unspoken punctuation, and a convolutional neural network (CNN) model for sound events classification. Live Caption integrates the signal from the three models to create a single caption track, where sound event tags, like [APPLAUSE] and [MUSIC], appear without interrupting the flow of speech recognition results. Punctuation symbols are predicted while text is updated in parallel.

Incoming sound is processed through a Sound Recognition and ASR feedback loop. The produced text or sound label is formatted and added to the caption.
For sound recognition, we leverage previous work that was done for sound events detection, using a model that was built on top of the AudioSet dataset. The Sound Recognition model is used not only to generate popular sound effect labels but also to detect speech periods. The full automatic speech recognition (ASR) RNN-T engine runs only during speech periods in order to minimize memory and battery usage. For example, when music is detected and speech is not present in the audio stream, the [MUSIC] label will appear on screen, and the ASR model will be unloaded. The ASR model is only loaded back into memory when speech is present in the audio stream again.

In order for Live Caption to be most useful, it should be able to run continuously for long periods of time. To do this, Live Caption’s ASR model is optimized for edge-devices using several techniques, such as neural connection pruning, which reduced the power consumption to 50% compared to the full sized speech model. Yet while the model is significantly more energy efficient, it still performs well for a variety of use cases, including captioning videos, recognizing short queries and narrowband telephony speech, while also being robust to background noise.

The text-based punctuation model was optimized for running continuously on-device using a smaller architecture than the cloud equivalent, and then quantized and serialized using the TensorFlow Lite runtime. As the caption is formed, speech recognition results are rapidly updated a few times per second. In order to save on computational resources and provide a smooth user experience, the punctuation prediction is performed on the tail of the text from the most recently recognized sentence, and if the next updated ASR results do not change that text, the previously punctuated results are retained and reused.

Looking forward
Live Caption is now available in English on Pixel 4 and will soon be available on Pixel 3 and other Android devices. We look forward to bringing this feature to more users by expanding its support to other languages and by further improving the formatting in order to improve the perceived accuracy and coherency of the captions, particularly for multi-speaker content.

Acknowledgements
The core team includes Robert Berry, Anthony Tripaldi, Danielle Cohen, Anna Belozovsky, Yoni Tsafir, Elliott Burford, Justin Lee, Kelsie Van Deman, Nicole Bleuel, Brian Kemler, and Benny Schlesinger. We would like to thank the Google Speech team, especially Qiao Liang, Arun Narayanan, and Rohit Prabhavalkar for their insightful work on the ASR model as well as Chung-Cheng Chiu from Google Brain Team; Dan Ellis and Justin Paul for their help with integrating the Sound Recognition model; Tal Remez for his help in developing the punctuation model; Kevin Rocard and Eric Laurent‎ for their help with the Android audio capture API; and Eugenio Marchiori, Shivanker Goel, Ye Wen, Jay Yoo, Asela Gunawardana, and Tom Hume for their help with the Android infrastructure work.

Source: Google AI Blog


Introducing the Schema-Guided Dialogue Dataset for Conversational Assistants



Today's virtual assistants help users to accomplish a wide variety of tasks, including finding flights, searching for nearby events and movies, making reservations, sourcing information from the web and more. They provide this functionality by offering a unified natural language interface to a wide variety of services across the web. Large-scale virtual assistants, like Google Assistant, need to integrate with a large and constantly increasing number of services, each with potentially overlapping functionality, over a wide variety of domains. Supporting new services with ease, without collection of additional data or retraining the model, and reducing maintenance workload are necessary to accommodate future growth. Despite tremendous progress, however, these challenges have often been overlooked in state-of-the-art models. This is due, in part, to the absence of suitable datasets that match the scale and complexity confronted by such virtual assistants.

In our recent paper, “Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset”, we introduce a new dataset to address these problems. The Schema-Guided Dialogue dataset (SGD) is the largest publicly available corpus of task-oriented dialogues, with over 18,000 dialogues spanning 17 domains. Equipped with various annotations, this dataset is designed to serve as an effective testbed for intent prediction, slot filling, state tracking (i.e., estimating the user's goal) and language generation, among other tasks for large-scale virtual assistants. We also propose a schema-guided approach for building virtual assistants as a solution to the aforementioned challenges. Our approach utilizes a single model across all services and domains, with no domain-specific parameters. Based on the schema-guided approach and building on the power of pre-trained language models like BERT, we open source a model for dialogue state tracking, which is applicable in a zero-shot setting (i.e., with no training data for new services and APIs) while remaining competitive in the regular setting.

The Dataset
The primary goal of releasing the SGD dataset is to confront many real-world challenges that are not sufficiently captured by existing datasets. The SGD dataset consists of over 18k annotated multi-domain, task-oriented conversations between a human and a virtual assistant. These conversations involve interactions with services and APIs spanning 17 domains, ranging from banks and events to media, calendar, travel, and weather. For most of these domains, the SGD dataset contains multiple different APIs, many of which have overlapping functionalities but different interfaces, which reflects common real-world scenarios. SGD is the first dataset to cover such a wide variety of domains and provide multiple APIs per domain. Furthermore, to quantify the robustness of models to changes in API interfaces or to the addition of new APIs, the evaluation set contains many new services that are not present in the training set.

For the creation of the SGD dataset, we have prioritized the variety and accuracy of annotations in the included dialogues. To begin with, dialogues were collected by interaction between two people using a Wizard-of-Oz style process, followed by crowdsourced annotation. Initial efforts revealed the difficulty in obtaining consistent annotations using this method, so we developed a new data collection process that minimized the need for complex manual annotation, and considerably reduced the time and cost of data collection.

For this alternate approach, we developed a multi-domain dialogue simulator that generates dialogue skeletons over an arbitrary combination of APIs, along with the corresponding annotations, such as dialogue state and system actions. The simulator consists of two agents playing the role of the user and the assistant. Both the agents interact with each other using a finite set of actions denoting dialogue semantics with transitions specified through a probabilistic automaton, designed to capture a wide variety of dialogue trajectories. The actions generated by the simulator are converted into natural language utterances using a set of templates. Crowdsourcing is used only for paraphrasing these templatized utterances in order to make the dialogue more natural and coherent. This setup eliminates the need for complicated domain-specific instructions while keeping the crowdsourcing task simple and yields natural dialogues with consistent, high quality annotations.
Steps for obtaining dialogues, with assistant turns marked in red and user turns in blue. Left: The simulator generates a dialogue skeleton using a finite set of actions. Center: Actions are converted into utterances using templates (~50 per service) and slot values are replaced with natural variations. Right: Paraphrasing via crowdsourcing to make the flow cohesive.
The Schema-Guided Approach
With the availability of the SGD dataset, it is now possible to train virtual assistants to support the diversity of services available on the web. A common approach to do this requires a large master schema that lists all supported functions and their parameters. However, it is difficult to develop a master schema catering to all possible use cases. Even if that problem is solved, a master schema would complicate integration of new or small-scale services and would increase the maintenance workload of the assistant. Furthermore, while there are many similar concepts across services that can be jointly modeled, for example, the similarities in logic for querying or specifying the number of movie tickets, flight tickets or concert tickets, the master schema approach does not facilitate joint modeling of such concepts, unless an explicit mapping between them is manually defined.

The new schema-guided approach we propose addresses these limitations. This approach does not require the definition of a master schema for the assistant. Instead, each service or API provides a natural language description of the functions listed in its schema along with their associated attributes. These descriptions are then used to learn a distributed semantic representation of the schema, which is given as an additional input to the dialogue system. The dialogue system is then implemented as a single unified model, containing no domain or service specific parameters. This unified model facilitates representation of common knowledge between similar concepts in different services, while the use of distributed representations of the schema makes it possible to operate over new services that are not present in the training data. We have implemented this approach in our open-sourced dialogue state tracking model.

Eighth Dialogue System Technology Challenge
The Dialog System Technology Challenges (DSTCs) are a series of research competitions to accelerate the development of new dialogue technologies. This year, Google organized one of the tracks, "Schema-Guided Dialogue State Tracking", as part of the recently concluded 8th DSTC. We received submissions from a total of 25 teams from both industry and academia, which will be presented at the DSTC8 workshop at AAAI-20.

We believe that this dataset will act as a good benchmark for building large-scale dialogue models. We are excited and looking forward to all the innovative ways in which the research community will use it for the advancement of dialogue technologies.

Acknowledgements
This post reflects the work of our co-authors Xiaoxue Zang, Srinivas Sunkara and Raghav Gupta. We also thank Amir Fayazi and Maria Wang for help with data collection and Guan-Lin Chao for insights on model design and implementation.

Source: Google AI Blog


Google at ICCV 2019



This week, Seoul, South Korea hosts the International Conference on Computer Vision 2019 (ICCV 2019), one of the world's premier conferences on computer vision. As a leader in computer vision research and a Gold Sponsor, Google will have a strong presence at ICCV 2019 with over 200 Googlers in attendance, more than 40 research presentations, and involvement in the organization of a number of workshops and tutorials.

If you are attending ICCV this year, please stop by our booth. There you can chat with researchers who are actively pursuing the latest innovations in computer vision and demo some of their latest research, including the technology behind MediaPipe, the new Open Images dataset, new developments for Google Lens and much more.

This year Google researchers are recipients of three prestigious ICCV awards:
More details about the Google research being presented at ICCV 2019 can be found below (Google affiliations in blue).

Organizing Committee includes:
Ming-Hsuan Yang (Program Chair)

Oral Presentations
Learning Single Camera Depth Estimation using Dual-Pixels
Rahul Garg, Neal Wadhwa, Sameer Ansari, Jonathan Barron 

RIO: 3D Object Instance Re-Localization in Changing Indoor Environments
Johanna Wald, Armen Avetisyan, Nassir Navab, Federico Tombari, Matthias Niessner 

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
Weicheng Kuo, Anelia Angelova, Jitendra Malik, Tsung-Yi Lin 

PuppetGAN: Cross-Domain Image Manipulation by Demonstration
Ben Usman, Nick Dufour, Kate Saenko, Chris Bregler

COCO-GAN: Generation by Parts via Conditional Coordinating
Chieh Hubert Lin, Chia-Che Chang, Yu-Sheng Chen, Da-Cheng Juan, Wei Wei, Hwann-Tzong Chen

Towards Unconstrained End-to-End Text Spotting
Siyang Qin, Alessandro Bissaco, Michalis Raptis, Yasuhisa Fujii, Ying Xiao

SinGAN: Learning a Generative Model from a Single Natural Image
Tamar Rott Shaham, Tali Dekel, Tomer Michaeli 
(ICCV 2019 Marr Prize Winner — Best Paper Award)

Generative Modeling for Small-Data Object Detection
Lanlan Liu, Michael Muelly, Jia Deng, Tomas Pfister, Li-Jia Li 

Searching for MobileNetV3
Andrew Howard, Mark Sandler, Bo Chen, Weijun Wang, Liang-Chieh Chen, Mingxing Tan, Grace Chu, Vijay Vasudevan, Yukun Zhu, Ruoming Pang, Hartwig Adam, Quoc Le 

S⁴L: Self-Supervised Semi-supervised Learning
Lucas Beyer, Xiaohua Zhai, Avital Oliver, Alexander Kolesnikov 

Sampling-Free Epistemic Uncertainty Estimation Using Approximated Variance Propagation
Janis Postels, Francesco Ferroni, Huseyin Coskun, Nassir Navab, Federico Tombari

Linearized Multi-sampling for Differentiable Image Transformation
Wei Jiang, Weiwei Sun, Andrea Tagliasacchi, Eduard Trulls, Kwang Moo Yi 

Poster Presentations
ELF: Embedded Localisation of Features in Pre-trained CNN
Assia Benbihi, Matthieu Geist, Cedric Pradalier 

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras
Ariel Gordon, Hanhan Li, Rico Jonschkowski, Anelia Angelova

ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image
Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari 

A Learned Representation for Scalable Vector Graphics
Raphael Gontijo Lopes, David Ha, Douglas Eck, Jonathon Shlens 

FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
Jingwei Huang, Yichao Zhou, Thomas Funkhouser, Leonidas Guibas

Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Yuyin Zhou, Zhe Li, Song Bai, Xinlei Chen, Mei Han, Chong Wang, Elliot Fishman, Alan Yuille 

Boundless: Generative Adversarial Networks for Image Extension
Dilip Krishnan, Piotr Teterwak, Aaron Sarna, Aaron Maschinot, Ce Liu, David Belanger, William Freeman

Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Keren Ye, Mingda Zhang, Adriana Kovashka, Wei Li, Danfeng Qin, Jesse Berent 

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-supervised Object Detection
Jiyang Gao, Jiang Wang, Shengyang Dai, Li-Jia Li, Ram Nevatia 

Object-Driven Multi-Layer Scene Decomposition from a Single Image
Helisa Dhamo, Nassir Navab, Federico Tombari 

Improving Adversarial Robustness via Guided Complement Entropy
Hao-Yun Chen, Jhao-Hong Liang, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan 

XRAI: Better Attributions Through Regions
Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viegas, Michael Terry

SegSort: Segment Sorting for Semantic Segmentation
Jyh-Jing Hwang, Stella Yu, Jianbo Shi, Maxwell Collins, Tien-Ju Yang, Xiao Zhang, Liang-Chieh Chen 

Self-Supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera
Yuhua Chen, Cordelia Schmid, Cristian Sminchisescu 

VideoBERT: A Joint Model for Video and Language Representation Learning
Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy, Cordelia Schmid 

Explaining the Ambiguity of Object Detection and 6D Pose from Visual Data
Fabian Manhardt, Diego Martín Arroyo, Christian Rupprecht, Benjamin  Busam, Tolga Birdal, Nassir Navab, Federico Tombari 

Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation
Qing Lian, Lixin Duan, Fengmao Lv, Boqing Gong 

Learning Shape Templates Using Structured Implicit Functions
Kyle Genova, Forrester Cole, Daniel Vlasic, Aaron Sarna, William Freeman, Thomas Funkhouser

Transferable Representation Learning in Vision-and-Language Navigation
Haoshuo Huang, Vihan Jain, Harsh Mehta, Alexander Ku, Gabriel Magalhaes, Jason Baldridge, Eugene Ie 

Controllable Attention for Structured Layered Video Decomposition
Jean-Baptiste Alayrac, Joao Carreira, Relja Arandjelović, Andrew Zisserman

Pixel2Mesh++: Multi-view 3D Mesh Generation via Deformation
Chao Wen, Yinda Zhang, Zhuwen Li, Yanwei Fu

Beyond Cartesian Representations for Local Descriptors
Patrick Ebel, Anastasiia Mishchuk, Kwang Moo Yi, Pascal Fua, Eduard Trulls

Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data
Xiangyu Yue, Yang Zhang, Sicheng Zhao, Alberto Sangiovanni-Vincentelli, Kurt Keutzer, Boqing Gong 

Evolving Space-Time Neural Architectures for Videos
AJ Piergiovanni, Anelia Angelova, Alexander Toshev, Michael Ryoo 

Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
Valentin Gabeur, Jean-Sebastien Franco, Xavier Martin, Cordelia Schmid, Gregory Rogez

Multi-view Image Fusion
Marc Comino Trinidad, Ricardo Martin-Brualla, Florian Kainz, Janne Kontkanen 

EvalNorm: Estimating Batch Normalization Statistics for Evaluation
Saurabh Singh, Abhinav Shrivastava

Attention Augmented Convolutional Networks
Irwan Bello, Barret Zoph, Quoc Le, Ashish Vaswani, Jonathon Shlens 

Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams
Yuning Chai

Workshops
Low-Power Computer Vision
Organizers include: Bo Chen

Neural Architects
Organizers include: Barret Zoph

The 3rd YouTube-8M Large-Scale Video Understanding Workshop
Organizers include: Paul NatsevCordelia SchmidRahul SukthankarJoonseok LeeGeorge Toderici

Should We Pre-register Experiments in Computer Vision?
Organizers include: Jack Valmadre

Extreme Vision Modeling
Organizers include: Rahul Sukthankar

Joint COCO and Mapillary Recognition Challenge
Organizers include: Tsung-Yi Lin, Yin Cui

Open Images Challenge
Organizers include: Vittorio Ferrari, Alina Kuznetsova, Rodrigo Benenson, Victor Gomes, Matteo Malloci

Tutorials
Meta-Learning and Metric Learning Algorithms
Organizers include: Kevin Swersky

Source: Google AI Blog


A New Workflow for Collaborative Machine Learning Research in Biodiversity



The promise of machine learning (ML) for species identification is coming to fruition, revealing its transformative potential in biodiversity research. International workshops such as FGVC and LifeCLEF feature competitions to develop top performing classification algorithms for everything from wildlife camera trap images to pressed flower specimens on herbarium sheets. The encouraging results that have emerged from these competitions inspired us to expand the availability of biodiversity datasets and ML models from workshop-scale to global-scale.

Bringing powerful ML algorithms to the communities that need them requires more than the traditional “big data + big compute” equation. Institutions ranging from natural history museums to citizen science groups take great care to collect and annotate datasets, and the data they share have enabled numerous scientific research publications. But central to the tradition of scholarly research are the conventions of citation and attribution, and it follows that as ML extends its reach into the life sciences, it should bring with it appropriate counterparts to those conventions. More broadly, there is a growing awareness of the importance of ethics, fairness, and transparency within the ML community. As institutions develop and deploy applications of ML at scale, it is critical that they be designed with these considerations in mind.

This week at Biodiversity Next, in collaboration with the Global Biodiversity Information Facility (GBIF), iNaturalist, and Visipedia, we are announcing a new workflow for biodiversity research institutions who would like to make use of ML. With its billion+ species occurrence count contributed by thousands of institutions around the globe, GBIF is playing a vital role in enabling this workflow, whether in terms of data aggregation, collaboration across teams, or standardizing citation practices. In the short term, the most important role relates to an emerging cultural shift in accepted practices for the use of mediated data for training of ML models. In the process of data mediation, GBIF helps ensure that training datasets for ML follow standardized licensing terms, use compatible taxonomies and data formats, and provide fair and sufficient data coverage for the ML task at hand by potentially sampling from multiple source datasets.

This new workflow comprises the following two components:
  1. To assist in developing and refining machine vision models, GBIF will package datasets, taking care to ensure license and citation practice are respected. The training datasets will be issued a Digital Object Identifier (DOI), and will be linked through the DOI citation graph.
  2. To assist application developers, Google and Visipedia will train and publish publicly accessible models with documentation on TensorFlow Hub. These models can then, in turn, be deployed in biodiversity research and citizen science efforts.
Case Study: Recognizing Fungi Species from Photos with the Interactive Mushroom Recognizer
As an illustration of the above workflow, we present an example of fungi recognition. The dataset in this case is curated by the Danish Mycological Society, and formatted, packaged, and shared by GBIF. The dataset provenance, model architecture, license information, and more can be found on the TF Hub model page, along with a live, interactive demonstration of the model that can run on user-supplied images.
Illustration of live, interactive Mushroom Recognizer, powered by a publicly available model trained on a fungi dataset provided by the Danish Mycological Society.
Invitation to Participate
For more information about this initiative, please visit the project page at GBIF. We look forward to engaging with institutions around the globe to enable new and innovative uses of ML for biodiversity.

Acknowledgements
We’d like to thank our collaborators at GBIF, iNaturalist, and Visipedia for working together to develop this workflow. At Google we would like to thank Christine Kaeser-Chen, Chenyang Zhang, Yulong Liu, Kiat Chuan Tan, Christy Cui, Arvi Gjoka, Denis Brulé, Cédric Deltheil, Clément Beauseigneur, Grace Chu, Andrew Howard, Sara Beery, and Katherine Chou.

Source: Google AI Blog


Learning to Smell: Using Deep Learning to Predict the Olfactory Properties of Molecules



Smell is a sense shared by an incredible range of living organisms, and plays a critical role in how they analyze and react to the world. For humans, our sense of smell is tied to our ability to enjoy food and can also trigger vivid memories. Smell allows us to appreciate all of the fragrances that abound in our everyday lives, be they the proverbial roses, a batch of freshly baked cookies, or a favorite perfume. Yet despite its importance, smell has not received the same level of attention from machine learning researchers as have vision and hearing.

Odor perception in humans is the result of the activation of 400 different types of olfactory receptors (ORs), expressed in 1 million olfactory sensory neurons (OSNs), in a small patch of tissue called the olfactory epithelium. These OSNs send signals to the olfactory bulb, and then to further structures in the brain. Based on analogous advances in deep learning for sight and sound, it should be possible to directly predict the end sensory result of an input molecule, even without knowing the intricate details of all the systems involved. Solving the odor prediction problem would aid in discovering new synthetic odorants, thereby reducing the ecological impact of harvesting natural products. Inspection of the resulting olfactory models may even lead to new insights into the biology of smell.

Small odorant molecules are the most basic building blocks of flavors and fragrances, and therefore represent the simplest version of the odor prediction problem. Yet each molecule can have multiple odor descriptors. Vanillin, for example, has descriptors such as sweet, vanilla, creamy, and chocolate, with some notes being more apparent than others. So odor prediction is also a multi-label classification problem.

In “Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules”, we leverage graph neural networks (GNNs), a kind of deep neural network designed to operate on graphs as input, to directly predict the odor descriptors for individual molecules, without using any handcrafted rules. We demonstrate that this approach yields significantly improved performance in odor prediction compared to current state-of-the-art and is a promising direction for future research.

Graph Neural Networks for Odor Prediction
Since molecules are analogous to graphs, with atoms forming the vertices and bonds forming the edges, GNNs are the natural model of choice for their understanding. But how does one translate the structure of a molecule into a graph representation? Initially, every node in the graph is represented as a vector, using any preferred featurization — atom identity, atom charge, etc. Then, in a series of message passing steps, every node broadcasts its current vector value to each of its neighbors. An update function then takes the collection of vectors sent to it, and generates an updated vector value. This process can be repeated many times, until finally all of the nodes in the graph are summarized into a single vector via summing or averaging. That single vector, representing the entire molecule, can then be passed into a fully connected network as a learned molecular featurization. This network outputs a prediction for odor descriptors, as provided by perfume experts.
Each node is represented as a vector, and each entry in the vector initially encodes some atomic-level information.
For each node we look at adjacent nodes and collect their information, which is then transformed with a neural network into new information for the centered node. This procedure is performed iteratively. Other variants of GNNs utilize edge and graph-level information.
Illustration of a GNN for odor prediction. We translate the structure of molecules into graphs that are fed into GNN layers to learn a better representation of the nodes. These nodes are reduced into a single vector and passed into a neural network that is used to predict multiple odor descriptors.
This representation doesn’t know anything about spatial positions of atoms, and so it can’t distinguish stereoisomers, molecules made of the same atoms but in slightly different configurations that can smell different, such as (R)- and (S)-carvone. Nevertheless, we have found that even without distinguishing stereoisomers, in practice it is still possible to predict odor quite well.

For odor prediction, GNNs consistently demonstrate improved performance compared to previous state-of-the-art methods, such as random forests, which do not directly encode graph structure. The magnitude of the improvement depends on which odor one tries to predict.
Example of the performance of a GNN on odor descriptors against a strong baseline, as measured by the AUROC score. Example odor descriptors are picked randomly. Closer to 1.0 means better. In the majority of cases GNNs outperform the field-standard baseline substantially, with similar performance seen against other metrics (e.g., AUPRC, recall, precision).
Learning from the Model, and Extending It to Other Tasks
In addition to predicting odor descriptors, GNNs can be applied to other olfaction tasks. For example, take the case of classifying new or refined odor descriptors using only limited data. For each molecule, we extract a learned representation from an intermediate layer of the model that is optimized for our odor descriptors, which we call an “odor embedding”. One can think of this as an olfaction version of a color space, like RGB or CMYK. To see if this odor embedding is useful for predicting related but different tasks, we designed experiments that test our learned embedding on related tasks for which it was not originally designed. We then compared the performance of our odor embedding representation to a common chemoinformatic representation that encodes structural information of a molecule, but is agnostic to odor and found that the odor embedding generalized to several challenging new tasks, even matching state-of-the-art on some.
2D snapshot of our embedding space with some example odors highlighted. Left: Each odor is clustered in its own space. Right: The hierarchical nature of the odor descriptor. Shaded and contoured areas are computed with a kernel-density estimate of the embeddings.
Future Work
Within the realm of machine learning, smell remains the most elusive of the senses, and we’re excited to continue doing a small part to shed light on it through further fundamental research. The possibilities for future research are numerous, and touch on everything from designing new olfactory molecules that are cheaper and more sustainably produced, to digitizing scent, or even one day giving those without a sense of smell access to roses (and, unfortunately, also rotten eggs). We hope to also bring this problem to the attention of more of the machine learning world through the eventual creation and sharing of high-quality, open datasets.

Acknowledgements
This early research is the result of the work and advisement of a team of talented researchers and engineers in Google Brain — Benjamin Sanchez-Lengeling, Jennifer Wei, Brian Lee, Emily Reif, Carey Radebaugh, Max Bileschi, Yoni Halpern, and D. Sculley. We are delighted to have collaborated on this work with Richard Gerkin at ASU and Alán Aspuru-Guzik at the University of Toronto. We are of course building on an enormous amount of prior work, and have benefitted particularly from work by Justin Gilmer, George Dahl and others on fundamental methodology in GNNs, among many other works in neuroscience, statistics and chemistry. We are also grateful to helpful comments from Steven Kearnes, David Belanger, Joel Mainland, and Emily Mayhew.

Source: Google AI Blog


Quantum Supremacy Using a Programmable Superconducting Processor



Physicists have been talking about the power of quantum computing for over 30 years, but the questions have always been: will it ever do something useful and is it worth investing in? For such large-scale endeavors it is good engineering practice to formulate decisive short-term goals that demonstrate whether the designs are going in the right direction. So, we devised an experiment as an important milestone to help answer these questions. This experiment, referred to as a quantum supremacy experiment, provided direction for our team to overcome the many technical challenges inherent in quantum systems engineering to make a computer that is both programmable and powerful. To test the total system performance we selected a sensitive computational benchmark that fails if just a single component of the computer is not good enough.

Today we published the results of this quantum supremacy experiment in the Nature article, “Quantum Supremacy Using a Programmable Superconducting Processor”. We developed a new 54-qubit processor, named “Sycamore”, that is comprised of fast, high-fidelity quantum logic gates, in order to perform the benchmark testing. Our machine performed the target computation in 200 seconds, and from measurements in our experiment we determined that it would take the world’s fastest supercomputer 10,000 years to produce a similar output.
Left: Artist's rendition of the Sycamore processor mounted in the cryostat. (Full Res Version; Forest Stearns, Google AI Quantum Artist in Residence) Right: Photograph of the Sycamore processor. (Full Res Version; Erik Lucero, Research Scientist and Lead Production Quantum Hardware)
The Experiment
To get a sense of how this benchmark works, imagine enthusiastic quantum computing neophytes visiting our lab in order to run a quantum algorithm on our new processor. They can compose algorithms from a small dictionary of elementary gate operations. Since each gate has a probability of error, our guests would want to limit themselves to a modest sequence with about a thousand total gates. Assuming these programmers have no prior experience, they might create what essentially looks like a random sequence of gates, which one could think of as the “hello world” program for a quantum computer. Because there is no structure in random circuits that classical algorithms can exploit, emulating such quantum circuits typically takes an enormous amount of classical supercomputer effort.

Each run of a random quantum circuit on a quantum computer produces a bitstring, for example 0000101. Owing to quantum interference, some bitstrings are much more likely to occur than others when we repeat the experiment many times. However, finding the most likely bitstrings for a random quantum circuit on a classical computer becomes exponentially more difficult as the number of qubits (width) and number of gate cycles (depth) grow.
Process for demonstrating quantum supremacy.
In the experiment, we first ran random simplified circuits from 12 up to 53 qubits, keeping the circuit depth constant. We checked the performance of the quantum computer using classical simulations and compared with a theoretical model. Once we verified that the system was working, we ran random hard circuits with 53 qubits and increasing depth, until reaching the point where classical simulation became infeasible.
Estimate of the equivalent classical computation time assuming 1M CPU cores for quantum supremacy circuits as a function of the number of qubits and number of cycles for the Schrödinger-Feynman algorithm. The star shows the estimated computation time for the largest experimental circuits.
This result is the first experimental challenge against the extended Church-Turing thesis, which states that classical computers can efficiently implement any “reasonable” model of computation. With the first quantum computation that cannot reasonably be emulated on a classical computer, we have opened up a new realm of computing to be explored.

The Sycamore Processor
The quantum supremacy experiment was run on a fully programmable 54-qubit processor named “Sycamore.” It’s comprised of a two-dimensional grid where each qubit is connected to four other qubits. As a consequence, the chip has enough connectivity that the qubit states quickly interact throughout the entire processor, making the overall state impossible to emulate efficiently with a classical computer.

The success of the quantum supremacy experiment was due to our improved two-qubit gates with enhanced parallelism that reliably achieve record performance, even when operating many gates simultaneously. We achieved this performance using a new type of control knob that is able to turn off interactions between neighboring qubits. This greatly reduces the errors in such a multi-connected qubit system. We made further performance gains by optimizing the chip design to lower crosstalk, and by developing new control calibrations that avoid qubit defects.

We designed the circuit in a two-dimensional square grid, with each qubit connected to four other qubits. This architecture is also forward compatible for the implementation of quantum error-correction. We see our 54-qubit Sycamore processor as the first in a series of ever more powerful quantum processors.
Heat map showing single- (e1; crosses) and two-qubit (e2; bars) Pauli errors for all qubits operating simultaneously. The layout shown follows the distribution of the qubits on the processor. (Courtesy of Nature magazine.)

Testing Quantum Physics
To ensure the future utility of quantum computers, we also needed to verify that there are no fundamental roadblocks coming from quantum mechanics. Physics has a long history of testing the limits of theory through experiments, since new phenomena often emerge when one starts to explore new regimes characterized by very different physical parameters. Prior experiments showed that quantum mechanics works as expected up to a state-space dimension of about 1000. Here, we expanded this test to a size of 10 quadrillion and find that everything still works as expected. We also tested fundamental quantum theory by measuring the errors of two-qubit gates and finding that this accurately predicts the benchmarking results of the full quantum supremacy circuits. This shows that there is no unexpected physics that might degrade the performance of our quantum computer. Our experiment therefore provides evidence that more complex quantum computers should work according to theory, and makes us feel confident in continuing our efforts to scale up.

Applications
The Sycamore quantum computer is fully programmable and can run general-purpose quantum algorithms. Since achieving quantum supremacy results last spring, our team has already been working on near-term applications, including quantum physics simulation and quantum chemistry, as well as new applications in generative machine learning, among other areas.

We also now have the first widely useful quantum algorithm for computer science applications: certifiable quantum randomness. Randomness is an important resource in computer science, and quantum randomness is the gold standard, especially if the numbers can be self-checked (certified) to come from a quantum computer. Testing of this algorithm is ongoing, and in the coming months we plan to implement it in a prototype that can provide certifiable random numbers.

What’s Next?
Our team has two main objectives going forward, both towards finding valuable applications in quantum computing. First, in the future we will make our supremacy-class processors available to collaborators and academic researchers, as well as companies that are interested in developing algorithms and searching for applications for today’s NISQ processors. Creative researchers are the most important resource for innovation — now that we have a new computational resource, we hope more researchers will enter the field motivated by trying to invent something useful.

Second, we’re investing in our team and technology to build a fault-tolerant quantum computer as quickly as possible. Such a device promises a number of valuable applications. For example, we can envision quantum computing helping to design new materials — lightweight batteries for cars and airplanes, new catalysts that can produce fertilizer more efficiently (a process that today produces over 2% of the world’s carbon emissions), and more effective medicines. Achieving the necessary computational capabilities will still require years of hard engineering and scientific work. But we see a path clearly now, and we’re eager to move ahead.

Acknowledgements
We’d like to thank our collaborators and contributors — University of California Santa Barbara, NASA Ames Research Center, Oak Ridge National Laboratory, Forschungszentrum Jülich, and many others who helped along the way.


Source: Google AI Blog


Audio and Visual Quality Measurement using Fréchet Distance



"I often say that when you can measure what you are speaking about, and express it in numbers, you know something about it; but when you cannot measure it, when you cannot express it in numbers, your knowledge is of a meagre and unsatisfactory kind.”
    William Thomson (Lord Kelvin), Lecture on "Electrical Units of Measurement" (3 May 1883), published in Popular Lectures Vol. I, p. 73
The rate of scientific progress in machine learning has often been determined by the availability of good datasets, and metrics. In deep learning, benchmark datasets such as ImageNet or Penn Treebank were among the driving forces that established deep artificial neural networks for image recognition and language modeling. Yet, while the available “ground-truth” datasets lend themselves nicely as measures of performance on these prediction tasks, determining the “ground-truth” for comparison to generative models is not so straightforward. Imagine a model that generates videos of StarCraft video game sequences — how does one determine which model is best? Clearly some of the videos shown below look more realistic than others, but can the differences between them be quantified? Access to robust metrics for evaluation of generative models is crucial for measuring (and making) progress in the fields of audio and video understanding, but currently no such metrics exist.
Videos generated from various models trained on sequences from the StarCraft Video (SCV) dataset.
In “Fréchet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms” and “Towards Accurate Generative Models of Video: A New Metric & Challenges”, we present two such metrics — the Fréchet Audio Distance (FAD) and Fréchet Video Distance (FVD). We document our large-scale human evaluations using 10k video and 69k audio clip pairwise comparisons that demonstrate high correlations between our metrics and human perception. We are also releasing the source code for both Fréchet Video Distance and Fréchet Audio Distance on github (FVD; FAD).

General Description of Fréchet Distance
The goal of a generative model is to learn to produce samples that look similar to the ones on which it has been trained, such that it knows what properties and features are likely to appear in the data, and which ones are unlikely. In other words, a generative model must learn the probability distribution of the training data. In many cases, the target distributions for generative models are very high-dimensional. For example, a single image of 128x128 pixels with 3 color channels has almost 50k dimensions, while a second-long video clip might consist of dozens (or hundreds) of such frames with audio that may have 16,000 samples. Calculating distances between such high dimensional distributions in order to quantify how well a given model succeeds at a task is very difficult. In the case of pictures, one could look at a few samples to gauge visual quality, but doing so for every model trained is not feasible.

In addition, generative adversarial networks (GANs) tend to focus on a few modes of the overall target distribution, while completely ignoring others. For example, they may learn to generate only one type of object or only a select few viewing angles. As a consequence, looking only at a limited number of samples from the model may not indicate whether the network learned the entire distribution successfully. To remedy this, a metric is needed that aligns well with human judgement of quality, while also taking the properties of the target distribution into account.

One common solution for this problem is the so-called Fréchet Inception Distance (FID) metric, which was specifically designed for images. The FID takes a large number of images from both the target distribution and the generative model, and uses the Inception object-recognition network to embed each image into a lower-dimensional space that captures the important features. Then it computes the so-called Fréchet distance between these samples, which is a common way of calculating distances between distributions that provides a quantitative measure of how similar the two distributions actually are.
A key component for both metrics is a pre-trained model that converts the video or audio clip into an N-dimensional embedding.
Fréchet Audio Distance and Fréchet Video Distance
Building on the principles of FID that have been successfully applied to the image domain, we propose both Fréchet Video Distance (FVD) and Fréchet Audio Distance (FAD). Unlike popular metrics such as peak signal-to-noise ratio or the structural similarity index, FVD looks at videos in their entirety, and thereby avoids the drawbacks of framewise metrics.
Examples of videos of a robot arm, judged by the new FVD metric. FVD values were found to be approximately 2000, 1000, 600, 400, 300 and 150 (left-to-right; top-to-bottom). A lower FVD clearly correlates with higher video quality.
In the audio domain, existing metrics either require a time-aligned ground truth signal, such as source-to-distortion ratio (SDR), or only target a specific domain, like speech quality. FAD on the other hand is reference-free and can be used on any type of audio.

Below is a 2-D visualization of the audio embedding vectors from which we compute the FAD. Each point corresponds to the embedding of a 5-second audio clip, where the blue points are from clean music and other points represent audio that has been distorted in some way. The estimated multivariate Gaussian distributions are presented as concentric ellipses. As the magnitude of the distortions increase, the overlap between their distributions and that of the clean audio decreases. The separation between these distributions is what the Fréchet distance is measuring.
In the animation, we can see that as the magnitude of the distortions increases, the Gaussian distributions of the distorted audio overlaps less with the clean distribution. The magnitude of this separation is what the Fréchet distance is measuring.
Evaluation
It is important for FAD and FVD to closely track human judgement, since that is the gold standard for what looks and sounds “realistic”. So, we performed a large-scale human study to determine how well our new metrics align with qualitative human judgment of generated audio and video. For the study, human raters examined 10,000 video pairs and 69,000 5-second audio clips. For the FAD we asked human raters to compare the effect of two different distortions on the same audio segment, randomizing both the pair of distortions that they compared and the order in which they appeared. The raters were asked “Which audio clip sounds most like a studio-produced recording?” The collected set of pairwise evaluations was then ranked using a Plackett-Luce model, which estimates a worth value for each parameter configuration. Comparison of the worth values to the FAD demonstrates that the FAD correlates quite well with human judgement.
This figure compares the FAD calculated between clean background music and music distorted by a variety of methods (e.g., pitch down, Gaussian noise, etc.) to the associated worth values from human evaluation. Each type of distortion has two data points representing high and low extremes in the distortion applied. The quantization distortion (purple circles), for example, limits the audio to a specific number of bits per sample, where the two data points represent two different bitrates. Both human raters and the FAD assigned higher values (i.e., “less realistic”) to the lower bitrate quantization. Overall log FAD correlates well with human judgement — a perfect correlation between the log FAD and human perception would result in a straight line.
Conclusion
We are currently making great strides in generative models. FAD and FVD will help us keeping this progress measurable, and will hopefully lead us to improve our models for audio and video generation.

Acknowledgements
There are many people who contributed to this large effort, and we’d like to highlight some of the key contributors: Sjoerd van Steenkiste, Karol Kurach, Raphael Marinier, Marcin Michalski, Sylvain Gelly, Mauricio Zuluaga, Dominik Roblek, Matthew Sharifi as well as the extended Google Brain team in Zurich.

Source: Google AI Blog


Video Architecture Search



Video understanding is a challenging problem. Because a video contains spatio-temporal data, its feature representation is required to abstract both appearance and motion information. This is not only essential for automated understanding of the semantic content of videos, such as web-video classification or sport activity recognition, but is also crucial for robot perception and learning. Just like humans, an input from a robot’s camera is seldom a static snapshot of the world, but takes the form of a continuous video.

The abilities of today’s deep learning models are greatly dependent on their neural architectures. Convolutional neural networks (CNNs) for videos are normally built by manually extending known 2D architectures such as Inception and ResNet to 3D or by carefully designing two-stream CNN architectures that fuse together both appearance and motion information. However, designing an optimal video architecture to best take advantage of spatio-temporal information in videos still remains an open problem. Although neural architecture search (e.g., Zoph et al, Real et al) to discover good architectures has been widely explored for images, machine-optimized neural architectures for videos have not yet been developed. Video CNNs are typically computation- and memory-intensive, and designing an approach to efficiently search for them while capturing their unique properties has been difficult.

In response to these challenges, we have conducted a series of studies into automatic searches for more optimal network architectures for video understanding. We showcase three different neural architecture evolution algorithms: learning layers and their module configuration (EvaNet); learning multi-stream connectivity (AssembleNet); and building computationally efficient and compact networks (TinyVideoNet). The video architectures we developed outperform existing hand-made models on multiple public datasets by a significant margin, and demonstrate a 10x~100x improvement in network runtime.

EvaNet: The first evolved video architectures
EvaNet, which we introduce in “Evolving Space-Time Neural Architectures for Videos” at ICCV 2019, is the very first attempt to design neural architecture search for video architectures. EvaNet is a module-level architecture search that focuses on finding types of spatio-temporal convolutional layers as well as their optimal sequential or parallel configurations. An evolutionary algorithm with mutation operators is used for the search, iteratively updating a population of architectures. This allows for parallel and more efficient exploration of the search space, which is necessary for video architecture search to consider diverse spatio-temporal layers and their combinations. EvaNet evolves multiple modules (at different locations within the network) to generate different architectures.

Our experimental results confirm the benefits of such video CNN architectures obtained by evolving heterogeneous modules. The approach often finds that non-trivial modules composed of multiple parallel layers are most effective as they are faster and exhibit superior performance to hand-designed modules. Another interesting aspect is that we obtain a number of similarly well-performing, but diverse architectures as a result of the evolution, without extra computation. Forming an ensemble with them further improves performance. Due to their parallel nature, even an ensemble of models is computationally more efficient than the other standard video networks, such as (2+1)D ResNet. We have open sourced the code.
Examples of various EvaNet architectures. Each colored box (large or small) represents a layer with the color of the box indicating its type: 3D conv. (blue), (2+1)D conv. (orange), iTGM (green), max pooling (grey), averaging (purple), and 1x1 conv. (pink). Layers are often grouped to form modules (large boxes). Digits within each box indicate the filter size.
AssembleNet: Building stronger and better (multi-stream) models
In “AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures”, we look into a new method of fusing different sub-networks with different input modalities (e.g., RGB and optical flow) and temporal resolutions. AssembleNet is a “family” of learnable architectures that provide a generic approach to learn the “connectivity” among feature representations across input modalities, while being optimized for the target task. We introduce a general formulation that allows representation of various forms of multi-stream CNNs as directed graphs, coupled with an efficient evolutionary algorithm to explore the high-level network connectivity. The objective is to learn better feature representations across appearance and motion visual clues in videos. Unlike previous hand-designed two-stream models that use late fusion or fixed intermediate fusion, AssembleNet evolves a population of overly-connected, multi-stream, multi-resolution architectures while guiding their mutations by connection weight learning. We are looking at four-stream architectures with various intermediate connections for the first time — 2 streams per RGB and optical flow, each one at different temporal resolutions.

The figure below shows an example of an AssembleNet architecture, found by evolving a pool of random initial multi-stream architectures over 50~150 rounds. We tested AssembleNet on two very popular video recognition datasets: Charades and Moments-in-Time (MiT). Its performance on MiT is the first above 34%. The performances on Charades is even more impressive at 58.6% mean Average Precision (mAP), whereas previous best known results are 42.5 and 45.2.
The representative AssembleNet model evolved using the Moments-in-Time dataset. A node corresponds to a block of spatio-temporal convolutional layers, and each edge specifies their connectivity. Darker edges mean stronger connections. AssembleNet is a family of learnable multi-stream architectures, optimized for the target task.
A figure comparing AssembleNet with state-of-the-art, hand-designed models on Charades (left) and Moments-in-Time (right) datasets. AssembleNet-50 or AssembleNet-101 has an equivalent number of parameters to a two-stream ResNet-50 or ResNet-101.
Tiny Video Networks: The fastest video understanding networks
In order for a video CNN model to be useful for devices operating in a real-world environment, such as that needed by robots, real-time, efficient computation is necessary. However, achieving state-of-the-art results on video recognition tasks currently requires extremely large networks, often with tens to hundreds of convolutional layers, that are applied to many input frames. As a result, these networks often suffer from very slow runtimes, requiring at least 500+ ms per 1-second video snippet on a contemporary GPU and 2000+ ms on a CPU. In Tiny Video Networks, we address this by automatically designing networks that provide comparable performance at a fraction of the computational cost. Our Tiny Video Networks (TinyVideoNets) achieve competitive accuracy and run efficiently, at real-time or better speeds, within 37 to 100 ms on a CPU and 10 ms on a GPU per ~1 second video clip, achieving hundreds of times faster speeds than the other human-designed contemporary models.

These performance gains are achieved by explicitly considering the model run-time during the architecture evolution and forcing the algorithm to explore the search space while including spatial or temporal resolution and channel size to reduce computations. The below figure illustrates two simple, but very effective architectures, found by TinyVideoNet. Interestingly the learned model architectures have fewer convolutional layers than typical video architectures: Tiny Video Networks prefers lightweight elements, such as 2D pooling, gating layers, and squeeze-and-excitation layers. Further, TinyVideoNet is able to jointly optimize parameters and runtime to provide efficient networks that can be used by future network exploration.
TinyVideoNet (TVN) architectures evolved to maximize the recognition performance while keeping its computation time within the desired limit. For instance, TVN-1 (top) runs at 37 ms on a CPU and 10ms on a GPU. TVN-2 (bottom) runs at 65ms on a CPU and 13ms on a GPU.
CPU runtime of TinyVideoNet models compared to prior models (left) and runtime vs. model accuracy of TinyVideoNets compared to (2+1)D ResNet models (right). Note that TinyVideoNets take a part of this time-accuracy space where no other models exist, i.e., extremely fast but still accurate.
Conclusion
To our knowledge, this is the very first work on neural architecture search for video understanding. The video architectures we generate with our new evolutionary algorithms outperform the best known hand-designed CNN architectures on public datasets, by a significant margin. We also show that learning computationally efficient video models, TinyVideoNets, is possible with architecture evolution. This research opens new directions and demonstrates the promise of machine-evolved CNNs for video understanding.

Acknowledgements
This research was conducted by Michael S. Ryoo, AJ Piergiovanni, and Anelia Angelova. Alex Toshev and Mingxing Tan also contributed to this work. We thank Vincent Vanhoucke, Juhana Kangaspunta, Esteban Real, Ping Yu, Sarah Sirajuddin, and the Robotics at Google team for discussion and support.

Source: Google AI Blog


Exploring Massively Multilingual, Massive Neural Machine Translation



“... perhaps the way [of translation] is to descend, from each language, down to the common base of human communication — the real but as yet undiscovered universal language — and then re-emerge by whatever particular route is convenient.”Warren Weaver, 1949

Over the last few years there has been enormous progress in the quality of machine translation (MT) systems, breaking language barriers around the world thanks to the developments in neural machine translation (NMT). The success of NMT however, owes largely to the great amounts of supervised training data. But what about languages where data is scarce, or even absent? Multilingual NMT, with the inductive bias that “the learning signal from one language should benefit the quality of translation to other languages”, is a potential remedy.

Multilingual machine translation processes multiple languages using a single translation model. The success of multilingual training for data-scarce languages has been demonstrated for automatic speech recognition and text-to-speech systems, and by prior research on multilingual translation [1,2,3]. We previously studied the effect of scaling up the number of languages that can be learned in a single neural network, while controlling the amount of training data per language. But what happens once all constraints are removed? Can we train a single model using all of the available data, despite the huge differences across languages in data size, scripts, complexity and domains?

In “Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges” and follow-up papers [4,5,6,7], we push the limits of research on multilingual NMT by training a single NMT model on 25+ billion sentence pairs, from 100+ languages to and from English, with 50+ billion parameters. The result is an approach for massively multilingual, massive neural machine translation (M4) that demonstrates large quality improvements on both low- and high-resource languages and can be easily adapted to individual domains/languages, while showing great efficacy on cross-lingual downstream transfer tasks.

Massively Multilingual Machine Translation
Though data skew across language-pairs is a great challenge in NMT, it also creates an ideal scenario in which to study transfer, where insights gained through training on one language can be applied to the translation of other languages. On one end of the distribution, there are high-resource languages like French, German and Spanish where there are billions of parallel examples, while on the other end, supervised data for low-resource languages such as Yoruba, Sindhi and Hawaiian, is limited to a few tens of thousands.
The data distribution over all language pairs (in log scale) and the relative translation quality (BLEU score) of the bilingual baselines trained on each one of these specific language pairs.
Once trained using all of the available data (25+ billion examples from 103 languages), we observe strong positive transfer towards low-resource languages, dramatically improving the translation quality of 30+ languages at the tail of the distribution by an average of 5 BLEU points. This effect is already known, but surprisingly encouraging, considering the comparison is between bilingual baselines (i.e., models trained only on specific language pairs) and a single multilingual model with representational capacity similar to a single bilingual model. This finding hints that massively multilingual models are effective at generalization, and capable of capturing the representational similarity across a large body of languages.
Translation quality comparison of a single massively multilingual model against bilingual baselines that are trained for each one of the 103 language pairs.
In our EMNLP’19 paper [5], we compare the representations of multilingual models across different languages. We find that multilingual models learn shared representations for linguistically similar languages without the need for external constraints, validating long-standing intuitions and empirical results that exploit these similarities. In [6], we further demonstrate the effectiveness of these learned representations on cross-lingual transfer on downstream tasks.
Visualization of the clustering of the encoded representations of all 103 languages, based on representational similarity. Languages are color-coded by their linguistic family.
Building Massive Neural Networks
As we increase the number of low-resource languages in the model, the quality of high-resource language translations starts to decline. This regression is recognized in multi-task setups, arising from inter-task competition and the unidirectional nature of transfer (i.e., from high- to low-resource). While working on better learning and capacity control algorithms to mitigate this negative transfer, we also extend the representational capacity of our neural networks by making them bigger by increasing the number of model parameters to improve the quality of translation for high-resource languages.

Numerous design choices can be made to scale neural network capacity, including adding more layers or making the hidden representations wider. Continuing our study on training deeper networks for translation, we utilized GPipe [4] to train 128-layer Transformers with over 6 billion parameters. Increasing the model capacity resulted in significantly improved performance across all languages by an average of 5 BLEU points. We also studied other properties of very deep networks, including the depth-width trade-off, trainability challenges and design choices for scaling Transformers to over 1500 layers with 84 billion parameters.

While scaling depth is one approach to increasing model capacity, exploring architectures that can exploit the multi-task nature of the problem is a very plausible complementary way forward. By modifying the Transformer architecture through the substitution of the vanilla feed-forward layers with sparsely-gated mixture of experts, we drastically scale up the model capacity, allowing us to successfully train and pass 50 billion parameters, which further improved translation quality across the board.
Translation quality improvement of a single massively multilingual model as we increase the capacity (number of parameters) compared to 103 individual bilingual baselines.
Making M4 Practical
It is inefficient to train large models with extremely high computational costs for every individual language, domain or transfer task. Instead, we present methods [7] to make these models more practical by using capacity tunable layers to adapt a new model to specific languages or domains, without altering the original.

Next Steps
At least half of the 7,000 languages currently spoken will no longer exist by the end of this century*. Can multilingual machine translation come to the rescue? We see the M4 approach as a stepping stone towards serving the next 1,000 languages; starting from such multilingual models will allow us to easily extend to new languages, domains and down-stream tasks, even when parallel data is unavailable. Indeed the path is rocky, and on the road to universal MT many promising solutions appear to be interdisciplinary. This makes multilingual NMT a plausible test bed for machine learning practitioners and theoreticians interested in exploring the annals of multi-task learning, meta-learning, training dynamics of deep nets and much more. We still have a long way to go.

Acknowledgements
This effort is built on contributions from Naveen Arivazhagan, Dmitry Lepikhin, Melvin Johnson, Maxim Krikun, Mia Chen, Yuan Cao, Yanping Huang, Sneha Kudugunta, Isaac Caswell, Aditya Siddhant, Wei Wang, Roee Aharoni, Sébastien Jean, George Foster, Colin Cherry, Wolfgang Macherey, Zhifeng Chen and Yonghui Wu. We would also like to acknowledge support from the Google Translate, Brain, and Lingvo development teams, Jakob Uszkoreit, Noam Shazeer, Hyouk Joong Lee, Dehao Chen, Youlong Cheng, David Grangier, Colin Raffel, Katherine Lee, Thang Luong, Geoffrey Hinton, Manisha Jain, Pendar Yousefi and Macduff Hughes.


* The Cambridge Handbook of Endangered Languages (Austin and Sallabank, 2011).

Source: Google AI Blog