Google AI Blog: May 2020

DADS: Unsupervised Reinforcement Learning for Skill Discovery

Friday, May 29, 2020

Posted by Archit Sharma, AI Resident, Google Researchsupervisedreinforcement learninggrasping arbitrary objectslearning agile locomotionsensorsmanual-labelling of “goal” statesunsupervised learningintrinsiccuriosityresearchhas recentlyfocusedDynamics-Aware Unsupervised Discovery of SkillsEmergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning

The behavior on the left is random and unpredictable, while the behavior on the right demonstrates systematic motion with predictable changes in the environment. Our goal is to learn potentially useful behaviors such as those on the right, without engineered reward functions.

Overview of DADSencouraging diversity) (predictability)skill-dynamics network

An overview of DADS.

Humanoid

Ant discovers galloping (top left) and skipping (bottom left), Humanoid discovers different locomotive gaits (middle, sped up 2x), and D’Claw from ROBEL (right) discovers different ways to rotate an object, all using DADS. More sample videos are available here.

Model-Based Control Using Skill-Dynamicswithout executing it in the environmentmodel-based planning

Using the skills discovered by the agents, we can traverse an arbitrary sequence of checkpoints without any additional training. The plot on the right follows the agent’s traversal from one checkpoint to another.

Real-World ResultsEmergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement LearningD’KittyROBELemergence of complex behaviors

Using off-DADS, we train D’Kitty from ROBEL to acquire diverse locomotion behaviors, which can then be used for goal-navigation through model-based control.

Future WorkAcknowledgementsWe would like to thank our coauthors, Michael Ahn, Sergey Levine, Vikash Kumar, Shixiang Gu and Karol Hausman. We would also like to acknowledge the support and feedback provided by various members of the Google Brain team and the Robotics at Google team.

Federated Analytics: Collaborative Data Science without Data Collection

Wednesday, May 27, 2020

Posted by Daniel Ramage, Research Scientist and Stefano Mazzocchi, Software Engineer, Google ResearchFederated learningintroduced in 2017next wordsexpressionsGboard for Androidimproving the quality of smart repliesAndroid Messagesfederated analyticsOrigin of Federated AnalyticslearningFederated Analytics for Song Recognition MeasurementNow Playing featureUnder the hoodfederated learning and analytics serversecure aggregation protocolProtecting Federated Analytics with Secure Aggregationparticular songS_EmilyS_ZhengMS_EmilyMS_ZhengMmasked S_EmilyMS_ZhengMS_EmilyS_Zhengdifferential privacy

An illustration of the secure aggregation protocol, from the federated learning comic book.

Toward Learning and Analytics with Greater Privacyanytraining a character-level recurrent neural networkwhat patterns in the data are difficult for my model to recognize?user-level differentially private model trainingprivacy principlesdifferential privacy in the data centerduring data collectionintroduced in 2014local differential privacyAdvances and Open Problems in Federated LearningFederated Heavy Hitters Discovery with Differential PrivacyAcknowledgmentsThis post reflects the work of many people, including Blaise Agüera y Arcas, Galen Andrew, Sean Augenstein, Françoise Beaufays, Kallista Bonawitz, Mingqing Chen, Hubert Eichner, Úlfar Erlingsson, Christian Frank, Anna Goralska, Marco Gruteser, Alex Ingerman, Vladimir Ivanov, Peter Kairouz, Chloé Kiddon, Ben Kreuter, Alison Lentz, Wei Li, Xu Liu, Antonio Marcedone, Rajiv Mathews, Brendan McMahan, Tom Ouyang, Sarvar Patel, Swaroop Ramaswamy, Aaron Segal, Karn Seth, Haicheng Sun, Timon Van Overveldt, Sergei Vassilvitskii, Scott Wegner, Yuanbo Zhang, Li Zhang, and Wennan Zhu.

Evaluating Natural Language Generation with BLEURT

Tuesday, May 26, 2020

Posted by Thibault Sellam, Software Engineer and Ankur P. Parikh, Research Scientist, Google Researchtranslate textsummarize articlesengage in conversationcomment on picturesincreasinglyof sophisticationBLEUunreliable substitutesBLEURT: Learning Robust Metrics for Text GenerationACL 2020transfer learningGithubEvaluating NLG Systems

An example questionnaire used for human evaluation in machine translation.

precision

BLEU scores for three candidate sentences. Candidate 2 is semantically close to the reference, and yet its score is lower than Candidate 3.

Introducing BLEURTWMT Metrics Shared Task

Three candidate sentences rated by BLEURT. BLEURT captures that candidate 2 is similar to the reference, even though it contains more non-reference words than candidate 3.

BERTdomain driftquality drift

BLEURT's data generation process combines random perturbations and scoring with pre-existing metrics and models.

Experimentsthe original BERT paper

Results

Correlation between different metrics and human ratings on the WMT'19 Metrics Shared Task.

ConclusionAcknowledgementsThis project was co-advised by Dipanjan Das. We thank Slav Petrov, Eunsol Choi, Nicholas FitzGerald, Jacob Devlin, Madhavan Kidambi, Ming-Wei Chang, and all the members of the Google Research Language team.

Open-Sourcing BiT: Exploring Large-Scale Pre-training for Computer Vision

Thursday, May 21, 2020

Posted by Lucas Beyer and Alexander Kolesnikov, Research Engineers, Google Research, ZürichOpenImagesPlacesthis amount of labeled datapre-trainedImageNetBERTT5large-scaleBig Transfer (BiT): General Visual Representation LearningILSVRC-2012ObjectNetshare the best BiT modelscode in TF2, Jax, and PyTorchPre-trainingImageNet-21kJFTResNet

Left: In order to make effective use of a larger dataset for pre-training, one needs to increase model capacity. The red arrows exemplify this: small architectures (smaller point) become worse when pre-trained on the larger ImageNet-21k, whereas the larger architectures (larger points) improve. Right: Pre-training on a larger dataset alone does not necessarily result in improved performance, e.g., when going from ILSVRC-2012 to the relatively larger ImageNet-21k. However, by also increasing the computational budget and training for longer, the performance improvement is pronounced.

batch normalizationstabilizes training by normalizing activationsgroup normalizationweight standardization

Summary of our pre-training strategy: take a standard ResNet, increase depth and width, replace BatchNorm (BN) with GroupNorm and Weight Standardization (GNWS), and train on a very large and generic dataset for many more iterations.

Transfer LearningBERT“BiT-HyperRule”

Once the BiT model is pre-trained, it can be fine-tuned on any task, even if only few labeled examples are available.

The curves depict median accuracy over 5 independent runs (light points) when transferring to CIFAR-10 with only 1 or 5 images per class (10 or 50 images total). It is evident that large architectures pre-trained on large datasets are significantly more data-efficient.

VTAB-1kthe previous state-of-the-artPetsFlowersCIFARRetinaNetMSCOCO-2017

Left: Accuracy of BiT-L compared to the previous state-of-the-art general model on various standard computer vision benchmarks. Right: Results in average precision (AP) of using BiT as backbone for RetinaNet on MSCOCO-2017.

BiT-HyperRuleEvaluation with ObjectNetObjectNetprevious state-of-the-art

Results of BiT on the ObjectNet evaluation dataset. Left: top-5 accuracy, right: top-1 accuracy.

ConclusionreleaseTensorFlow2 tutorialAcknowledgementsWe would like to thank Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, and Neil Houlsby who have co-authored the BiT paper and been involved in all aspects of its development, as well as the Brain team in Zürich. We also would like to thank Andrei Giurgiu for his help in debugging input pipelines. We thank Tom Small for creating the animations used in this blogpost. Finally, we refer the interested reader to the related approaches in this direction by our colleagues in Google Research, Noisy Student, as well as Facebook Research’s highly relevant Exploring the Limits of Weakly Supervised Pretraining.

Announcing the 7th Fine-Grained Visual Categorization Workshop

Wednesday, May 20, 2020

Posted by Christine Kaeser-Chen, Software Engineer and Serge Belongie, Visiting Faculty, Google ResearchDanaus plexippusLimenitis archippusFGVCCUB7th Workshop on Fine-Grained Visual CategorizationIEEEComputer Vision and Pattern Recognition

The FGVC workshop at CVPR 2020 focuses on subordinate categories, including (from left to right) wildlife camera traps, plant pathology, birds, herbarium sheets, apparel, and museum artifacts.

Real-World Impact of the FGVC ChallengesFungi challengeDanish Mycological Societya team from Czech Technical University and the University of West Bohemiaa new workflowconference paperapp for AndroidiOSopen access modelTensorFlow Hub

The Svampeatlas app for mushroom recognition is a result of a Danish-Czech collaboration spun out of the FGVC 2018 Fungi challenge. The underlying model is now published on TF Hub. Images used with permission of the Danish Mycological Society.

iCassava Disease ChallengeMakerere UniversityNational Crops Resources Research Institute

Examples of cassava leaf disease represented in the 2019 iCassava challenge.

This Year’s ChallengesiWildCammaking generalization difficultusing informationbeyondthe image itselfiNaturalist competition datasets

Side-by-side comparison of image quality from iWildcam, captured from wildlife camera traps, (left) and iNaturalist (right), captured by conventional cameras. Images are from the 2020 iWildCam Challenge, and the iNaturalist competition datasets from 2017 and 2018.

Herbarium ChallengeNew York Botanical Garden

Representative examples of specimens from the 2020 Herbarium challenge. Images used with permission of the New York Botanical Garden.

iMat Fashioninstance segmentationiMetMetropolitan Museum of ArtSemi-Supervised AvesiNaturalistsemi-supervised learningPlant PathologyiCassavaInvitation to ParticipateAcknowledgementsWe’d like to thank our colleagues and friends on the FGVC7 organizing committee for working together to advance this important area. At Google we would like to thank Hartwig Adam, Kiat Chuan Tan, Arvi Gjoka, Kimberly Wilber, Sara Beery, Mikhail Sirotenko, Denis Brulé, Timnit Gebru, Ernest Mwebaze, Wojciech Sirko, Maggie Demkin.

Enabling E-Textile Microinteractions: Gestures and Light through Helical Structures

Friday, May 15, 2020

Posted by Alex Olwal, Research Scientist, Google Research

A scalable interactive E-textile architecture with embedded touch sensing, gesture recognition and visual feedback.

E-textile MicrointeractionsACM CHI 2020previously introduced E-textile architectureACM UIST 2018video about E-textile microinteractionsvideo about the E-textile architecture

E-textile microinteractions combining continuous sensing with discrete motion and grasps.

The Helical Sensing Matrix (HSM)capacitive sensinghelical sensing matrixtransmitreceive

Left: A Helical Sensing Matrix based on a 4×4 braid (8 conductive threads spiraled around the core). Magenta/cyan are conductive yarns, used as receive/transmit lines. Grey are passive yarns (cotton). Center: Flattened matrix, that illustrates the infinite number of 4×4 matrices (colored circles 0-F), which repeat along the length of the cord. Right: Yellow are fiber optic lines, which provide visual feedback.

Rotation Detection

Rotation is deduced from horizontal finger motion across the columns. The plots below show the relative capacitive signal strengths, which change with finger proximity.

Interaction Techniques and Design Guidelines

Simple gestures. We design for short interactions where the user either makes a single discrete gesture or performs a continuous manipulation.

Closed-loop feedback. We want to help the user discover functionality and get continuous feedback on their actions. Where possible, we provide visual, tactile, and audio feedback integrated in the device.

Our e-textile enables interaction based on capacitive sensing of proximity, contact area, contact time, roll, and pressure.

Braided fiber optics strands create the illusion of directional motion.

Motion Gestures (Flicks and Slides) and Grasping Styles (Pinch, Grab, Pinch)

Gesture elicitation study with imagined touch sensing.

Twelve participants (horizontal axis) performed 9 repetitions (animation) for the eight gestures (vertical axis). Each sub-image shows 16 overlaid feature vectors, interpolated to 80 observations over time.

User-Independent, Continuous Twist: Quantifying Precision and Speeduser-independent

Left: Weighted average subjective feedback. We mapped the 7-point Likert scale to a score in the range [-3, 3] and multiplied by the number of times the technique received that rating, and computed an average for all the scores. Right: Mean completion times for target distances show that Buttons were consistently slower.

Gesture Prototypes: Headphones, Hoodie Drawstrings, and Speaker Cord

Left: Tap = Play/Pause; Center: Double-tap = Next track; Right: Roll = Volume +/-

Interactive speaker cord for simultaneous use of continuous (twisting/rolling) and discrete gestures (pinch/pat) to control music playback.

Conclusions and Future DirectionsAcknowledgementsThis work is a collaboration across multiple teams at Google. Key contributors to the project include Alex Olwal, Thad Starner, Jon Moeller, Greg Priest-Dorman, Ben Carroll, and Gowa Mainini. We thank the Google ATAP Jacquard team for our collaboration, especially Shiho Fukuhara, Munehiko Sato, and Ivan Poupyrev. We thank Google Wearables, and Kenneth Albanowski and Karissa Sawyer, in particular. Finally, we would like to thank Mark Zarich for illustrations, Bryan Allen for videography, Frank Li for data processing, Mathieu Le Goc for valuable discussions, and Carolyn Priest-Dorman for textile advice.

Announcing Meta-Dataset: A Dataset of Datasets for Few-Shot Learning

Wednesday, May 13, 2020

Posted by Eleni Triantafillou, Student Researcher and Vincent Dumoulin, Research Scientist, Google Researchmanually annotated training datasparked interestMeta-Dataset: A Dataset of Datasets for Learning to Learn from Few ExamplesICLR 2020ImageNetCUB-200-2011FungipublicnotebookTensorFlowPyTorchBackground: Few-shot Classificationtest taskstest setsupport set query set Comparison of Meta-Dataset with Previous Benchmarksmini-ImageNetImageNetclass splitsRecentworks

Test tasks from mini-ImageNet. Each task is a classification problem between previously unseen (test) classes. The model can use the support set of a few labeled examples of the new classes to adapt to the task at hand and then predicts labels for the query examples of these new classes. The evaluation metric is the query set accuracy, averaged over examples within each task and across tasks.

recentpapers

Test tasks from Meta-Dataset. Contrary to the mini-ImageNet tasks shown above, different tasks here originate from (the test classes of) different datasets. Further, the number of classes and the support set sizes differ across tasks and the support sets might be class-imbalanced.

Initial Investigation and Findings on Meta-Datasetpre-trainingmeta-learningnearest-neighbor comparisonssurgeofattention1) Existing approaches have trouble leveraging heterogeneous training data sources.OmniglotQuickdraw

Comparison of test performance on each dataset after having trained on ImageNet (ILSVRC-2012) only or on all datasets.

2) Some models are more capable than others of exploiting additional data at test time.ProtoNetfo-Proto-MAML

Comparison of test performance averaged across different datasets to the number of examples available per class in test tasks (“shots”). Performance is measured in terms of class precision: the proportion of the examples of a class that are correctly labeled, averaged across classes.

3) The adaptation algorithm of a meta-learner is more heavily responsible for its performance than the fact that it is trained end-to-end (i.e. meta-trained).

Comparison of three different meta-learner variants to their corresponding inference-only baselines, when training on ImageNet (ILSVRC-1012) only or all datasets. Each bar represents the difference between meta-training and inference-only, so positive values indicate improved performance from meta-training.

Conclusiontaskconditioninghyperparameter tuningmeta-baselinefeature selectionAcknowledgementsMeta-Dataset was developed by Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol and Hugo Larochelle. We would like to thank Pablo Castro for his valuable guidance on this blog post, Chelsea Finn for fruitful discussions and ensuring the correctness of fo-MAML’s implementation, as well as Zack Nado and Dan Moldovan for the initial dataset code that was adapted, Cristina Vasconcelos for spotting an issue in the ranking of models and John Bronskill for suggesting that we experiment with a larger inner-loop learning rate for MAML which indeed significantly improved our fo-MAML results.

Blog