Timezone: »
Learning a visual concept from a small number of positive examples is a significant challenge for machine learning algorithms. Current methods typically fail to find the appropriate level of generalization in a concept hierarchy for a given set of visual examples. Recent work in cognitive science on Bayesian models of generalization addresses this challenge, but prior results assumed that objects were perfectly recognized. We present an algorithm for learning visual concepts directly from images, using probabilistic predictions generated by visual classifiers as the input to a Bayesian generalization model. As no existing challenge data tests this paradigm, we collect and make available a new, large-scale dataset for visual concept learning using the ImageNet hierarchy as the source of possible concepts, with human annotators to provide ground truth labels as to whether a new image is an instance of each concept using a paradigm similar to that used in experiments studying word learning in children. We compare the performance of our system to several baseline algorithms, and show a significant advantage results from combining visual classifiers with the ability to identify an appropriate level of abstraction using Bayesian generalization.
Author Information
Yangqing Jia (Alibaba Group)
Joshua T Abbott (UC Berkeley)
Joseph L Austerweil (University of Wisconsin, Madison)
As a computational cognitive psychologist, my research program explores questions at the intersection of perception and higher-level cognition. I use recent advances in statistics and computer science to formulate ideal learner models to see how they solve these problems and then test the model predictions using traditional behavioral experimentation. Ideal learner models help us understand the knowledge people use to solve problems because such knowledge must be made explicit for the ideal learner model to successfully produce human behavior. This method yields novel machine learning methods and leads to the discovery of new psychological principles.
Tom Griffiths (Princeton)
Trevor Darrell (UC Berkeley)
More from the Same Authors
-
2022 : Studying Bias in GANs through the Lens of Race »
Vongani Maluleke · Neerja Thakkar · Tim Brooks · Ethan Weber · Trevor Darrell · Alexei Efros · Angjoo Kanazawa · Devin Guillory -
2020 Poster: Auxiliary Task Reweighting for Minimum-data Learning »
Baifeng Shi · Judy Hoffman · Kate Saenko · Trevor Darrell · Huijuan Xu -
2020 Poster: Fighting Copycat Agents in Behavioral Cloning from Observation Histories »
Chuan Wen · Jierui Lin · Trevor Darrell · Dinesh Jayaraman · Yang Gao -
2019 : Poster Presentations »
Rahul Mehta · Andrew Lampinen · Binghong Chen · Sergio Pascual-Diaz · Jordi Grau-Moya · Aldo Faisal · Jonathan Tompson · Yiren Lu · Khimya Khetarpal · Martin Klissarov · Pierre-Luc Bacon · Doina Precup · Thanard Kurutach · Aviv Tamar · Pieter Abbeel · Jinke He · Maximilian Igl · Shimon Whiteson · Wendelin Boehmer · Raphaël Marinier · Olivier Pietquin · Karol Hausman · Sergey Levine · Chelsea Finn · Tianhe Yu · Lisa Lee · Benjamin Eysenbach · Emilio Parisotto · Eric Xing · Ruslan Salakhutdinov · Hongyu Ren · Anima Anandkumar · Deepak Pathak · Christopher Lu · Trevor Darrell · Alexei Efros · Phillip Isola · Feng Liu · Bo Han · Gang Niu · Masashi Sugiyama · Saurabh Kumar · Janith Petangoda · Johan Ferret · James McClelland · Kara Liu · Animesh Garg · Robert Lange -
2019 : Oral Presentations »
Janith Petangoda · Sergio Pascual-Diaz · Jordi Grau-Moya · Raphaël Marinier · Olivier Pietquin · Alexei Efros · Phillip Isola · Trevor Darrell · Christopher Lu · Deepak Pathak · Johan Ferret -
2019 Workshop: AI for Humanitarian Assistance and Disaster Response »
Ritwik Gupta · Robin Murphy · Trevor Darrell · Eric Heim · Zhangyang Wang · Bryce Goodman · Piotr Biliński -
2019 Poster: Compositional Plan Vectors »
Coline Devin · Daniel Geng · Pieter Abbeel · Trevor Darrell · Sergey Levine -
2019 Poster: Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity »
Deepak Pathak · Christopher Lu · Trevor Darrell · Phillip Isola · Alexei Efros -
2019 Spotlight: Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity »
Deepak Pathak · Christopher Lu · Trevor Darrell · Phillip Isola · Alexei Efros -
2018 : Research Panel »
Sinead Williamson · Barbara Engelhardt · Tom Griffiths · Neil Lawrence · Hanna Wallach -
2018 Poster: Speaker-Follower Models for Vision-and-Language Navigation »
Daniel Fried · Ronghang Hu · Volkan Cirik · Anna Rohrbach · Jacob Andreas · Louis-Philippe Morency · Taylor Berg-Kirkpatrick · Kate Saenko · Dan Klein · Trevor Darrell -
2017 : Invited Talk 7 »
Trevor Darrell -
2017 : Adaptive Deep Learning for Perception, Action, and Explanation, Trevor Darrell (UC Berkeley) »
Trevor Darrell -
2017 : Revealing human inductive biases and metacognitive processes with rational models »
Tom Griffiths -
2017 : On-Device ML Frameworks »
Jeff Gehlhaar · Yangqing Jia · Rajat Monga -
2017 : Caffe2: Lessons from Running Deep Learning on the World’s Smart Phones »
Yangqing Jia -
2017 : High performance ultra-low-precision convolutions on mobile devices »
Andrew Tulloch · Yangqing Jia -
2017 Poster: A graph-theoretic approach to multitasking »
Noga Alon · Daniel Reichman · Igor Shinkar · Tal Wagner · Sebastian Musslick · Jonathan D Cohen · Tom Griffiths · Biswadip dey · Kayhan Ozcimder -
2017 Oral: A graph-theoretic approach to multitasking »
Noga Alon · Daniel Reichman · Igor Shinkar · Tal Wagner · Sebastian Musslick · Jonathan D Cohen · Tom Griffiths · Biswadip dey · Kayhan Ozcimder -
2017 Poster: Toward Multimodal Image-to-Image Translation »
Jun-Yan Zhu · Richard Zhang · Deepak Pathak · Trevor Darrell · Alexei Efros · Oliver Wang · Eli Shechtman -
2016 : Invited Talk: Learning Adaptive Driving Models from Large-scale Video Datasets (Fisher Yu, Huazhe Xu, Dequan Wang, and Trevor Darrell, Berkeley) »
Trevor Darrell -
2016 : Bounded Optimality and Rational Metareasoning in Human Cognition »
Tom Griffiths -
2016 Workshop: The Future of Interactive Machine Learning »
Kory Mathewson @korymath · Kaushik Subramanian · Mark Ho · Robert Loftin · Joseph L Austerweil · Anna Harutyunyan · Doina Precup · Layla El Asri · Matthew Gombolay · Jerry Zhu · Sonia Chernova · Charles Isbell · Patrick M Pilarski · Weng-Keen Wong · Manuela Veloso · Julie A Shah · Matthew Taylor · Brenna Argall · Michael Littman -
2016 Workshop: Machine Learning for Intelligent Transportation Systems »
Li Erran Li · Trevor Darrell -
2016 Oral: Showing versus doing: Teaching by demonstration »
Mark Ho · Michael Littman · James MacGlashan · Fiery Cushman · Joseph L Austerweil -
2016 Poster: Showing versus doing: Teaching by demonstration »
Mark Ho · Michael Littman · James MacGlashan · Fiery Cushman · Joe Austerweil · Joseph L Austerweil -
2015 : Intro and Adapting Deep Networks Across Domains, Modalities, and Tasks »
Trevor Darrell -
2015 Workshop: Bounded Optimality and Rational Metareasoning »
Samuel J Gershman · Falk Lieder · Tom Griffiths · Noah Goodman -
2014 Poster: Algorithm selection by rational metareasoning as a model of human strategy selection »
Falk Lieder · Dillon Plunkett · Jessica B Hamrick · Stuart J Russell · Nicholas Hay · Tom Griffiths -
2014 Poster: Do Convnets Learn Correspondence? »
Jonathan L Long · Ning Zhang · Trevor Darrell -
2014 Poster: LSDA: Large Scale Detection through Adaptation »
Judy Hoffman · Sergio Guadarrama · Eric Tzeng · Ronghang Hu · Jeff Donahue · Ross Girshick · Trevor Darrell · Kate Saenko -
2014 Poster: Weakly-supervised Discovery of Visual Pattern Configurations »
Hyun Oh Song · Yong Jae Lee · Stefanie Jegelka · Trevor Darrell -
2012 Poster: Learning with Recursive Perceptual Representations »
Oriol Vinyals · Yangqing Jia · Li Deng · Trevor Darrell -
2012 Poster: Human memory search as a random walk in a semantic network »
Joshua T Abbott · Joseph L Austerweil · Tom Griffiths -
2012 Spotlight: Human memory search as a random walk in a semantic network »
Joshua T Abbott · Joseph L Austerweil · Tom Griffiths -
2012 Poster: Timely Object Recognition »
Sergey K Karayev · Tobi Baumgartner · Mario Fritz · Trevor Darrell -
2012 Poster: Burn-in, bias, and the rationality of anchoring »
Falk Lieder · Tom Griffiths · Noah Goodman -
2011 Workshop: Integrating Language and Vision »
Raymond Mooney · Trevor Darrell · Kate Saenko -
2011 Poster: A rational model of causal inference with continuous causes »
M Pacer · Tom Griffiths -
2011 Poster: An ideal observer model for identifying the reference frame of objects »
Joseph L Austerweil · Abram Friesen · Tom Griffiths -
2011 Poster: Heavy-tailed Distances for Gradient Based Image Descriptors »
Yangqing Jia · Trevor Darrell -
2011 Poster: Testing a Bayesian Measure of Representativeness Using a Large Image Database »
Joshua T Abbott · Katherine Heller · Zoubin Ghahramani · Tom Griffiths -
2010 Workshop: Transfer Learning Via Rich Generative Models. »
Russ Salakhutdinov · Ryan Adams · Josh Tenenbaum · Zoubin Ghahramani · Tom Griffiths -
2010 Spotlight: Learning invariant features using the Transformed Indian Buffet Process »
Joseph L Austerweil · Tom Griffiths -
2010 Poster: Factorized Latent Spaces with Structured Sparsity »
Yangqing Jia · Mathieu Salzmann · Trevor Darrell -
2010 Poster: Learning invariant features using the Transformed Indian Buffet Process »
Joseph L Austerweil · Tom Griffiths -
2010 Poster: Size Matters: Metric Visual Search Constraints from Monocular Metadata »
Mario J Fritz · Kate Saenko · Trevor Darrell -
2009 Workshop: Bounded-rational analyses of human cognition: Bayesian models, approximate inference, and the brain »
Noah Goodman · Edward Vul · Tom Griffiths · Josh Tenenbaum -
2009 Poster: Learning to Hash with Binary Reconstructive Embeddings »
Brian Kulis · Trevor Darrell -
2009 Poster: Neural Implementation of Hierarchical Bayesian Inference by Importance Sampling »
Lei ShiUpdateMe · Tom Griffiths -
2009 Spotlight: Neural Implementation of Hierarchical Bayesian Inference by Importance Sampling »
Lei ShiUpdateMe · Tom Griffiths -
2009 Spotlight: Learning to Hash with Binary Reconstructive Embeddings »
Brian Kulis · Trevor Darrell -
2009 Poster: An Additive Latent Feature Model for Transparent Object Recognition »
Mario J Fritz · Michael J Black · Gary R Bradski · Trevor Darrell -
2009 Poster: Differential Use of Implicit Negative Evidence in Generative and Discriminative Language Learning »
Anne Hsu · Tom Griffiths -
2009 Poster: Filtering Abstract Senses From Image Search Results »
Kate Saenko · Trevor Darrell -
2009 Oral: Differential Use of Implicit Negative Evidence in Generative and Discriminative Language Learning »
Anne Hsu · Tom Griffiths -
2009 Oral: An Additive Latent Feature Model for Transparent Object Recognition »
Mario J Fritz · Michael J Black · Gary R Bradski · Trevor Darrell -
2009 Poster: Nonparametric Latent Feature Models for Link Prediction »
Kurt T Miller · Tom Griffiths · Michael Jordan -
2009 Spotlight: Nonparametric Latent Feature Models for Link Prediction »
Kurt T Miller · Tom Griffiths · Michael Jordan -
2008 Workshop: Machine learning meets human learning »
Nathaniel D Daw · Tom Griffiths · Josh Tenenbaum · Jerry Zhu -
2008 Poster: Modeling the effects of memory on human online sentence processing with particle filters »
Roger Levy · Florencia Reali · Tom Griffiths -
2008 Oral: Modeling the effects of memory on human online sentence processing with particle filters »
Roger Levy · Florencia Reali · Tom Griffiths -
2008 Poster: How memory biases affect information transmission: A rational analysis of serial reproduction »
Jing Xu · Tom Griffiths -
2008 Poster: Analyzing human feature learning as nonparametric Bayesian inference »
Joseph L Austerweil · Tom Griffiths -
2008 Poster: A rational model of preference learning and choice prediction by children »
Chris Lucas · Tom Griffiths · Fei Xu · Christine Fawcett -
2008 Spotlight: Analyzing human feature learning as nonparametric Bayesian inference »
Joseph L Austerweil · Tom Griffiths -
2008 Spotlight: A rational model of preference learning and choice prediction by children »
Chris Lucas · Tom Griffiths · Fei Xu · Christine Fawcett -
2008 Spotlight: How memory biases affect information transmission: A rational analysis of serial reproduction »
Jing Xu · Tom Griffiths -
2008 Poster: Unsupervised Learning of Visual Sense Models for Polysemous Words »
Kate Saenko · Trevor Darrell -
2008 Poster: Modeling human function learning with Gaussian processes »
Tom Griffiths · Chris Lucas · Joseph Jay Williams · Michael Kalish -
2008 Spotlight: Unsupervised Learning of Visual Sense Models for Polysemous Words »
Kate Saenko · Trevor Darrell -
2007 Oral: Markov Chain Monte Carlo with People »
Adam Sanborn · Tom Griffiths -
2007 Poster: Markov Chain Monte Carlo with People »
Adam Sanborn · Tom Griffiths -
2007 Poster: A Probabilistic Approach to Language Change »
Alexandre Bouchard-Côté · Percy Liang · Tom Griffiths · Dan Klein -
2006 Poster: Approximate Correspondences in High Dimensions »
Kristen Grauman · Trevor Darrell -
2006 Poster: Particle Filtering for Nonparametric Bayesian Matrix Factorization »
Frank Wood · Tom Griffiths -
2006 Spotlight: Approximate Correspondences in High Dimensions »
Kristen Grauman · Trevor Darrell -
2006 Poster: Adaptor Grammars: A Framework for Specifying Compositional Nonparametric Bayesian Mod »
Mark Johnson · Tom Griffiths · Sharon Goldwater -
2006 Poster: A Nonparametric Bayesian Method for Inferring Features From Similarity Judgments »
Daniel Navarro · Tom Griffiths