Timezone: »
Poster
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Yu Sun · Xiaolong Wang · Zhuang Liu · John Miller · Alexei Efros · Moritz Hardt
Wed Jul 15 10:00 AM -- 10:45 AM & Wed Jul 15 11:00 PM -- 11:45 PM (PDT) @ Virtual #None
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.
Author Information
Yu Sun (UC Berkeley)
Xiaolong Wang (UC Berkeley)
Zhuang Liu (UC Berkeley)
John Miller (University of California, Berkeley)
Alexei Efros (UC Berkeley)
Moritz Hardt (University of California, Berkeley)
More from the Same Authors
-
2021 : Causal Inference Struggles with Agency on Online Platforms »
Smitha Milli · Luca Belli · Moritz Hardt -
2022 : Invited Talk 4: Alexei Efros »
Alexei Efros -
2021 Poster: Outside the Echo Chamber: Optimizing the Performative Risk »
John Miller · Juan Perdomo · Tijana Zrnic -
2021 Poster: Alternative Microfoundations for Strategic Classification »
Meena Jagadeesan · Celestine Mendler-Dünner · Moritz Hardt -
2021 Poster: Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization »
John Miller · Rohan Taori · Aditi Raghunathan · Shiori Sagawa · Pang Wei Koh · Vaishaal Shankar · Percy Liang · Yair Carmon · Ludwig Schmidt -
2021 Spotlight: Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization »
John Miller · Rohan Taori · Aditi Raghunathan · Shiori Sagawa · Pang Wei Koh · Vaishaal Shankar · Percy Liang · Yair Carmon · Ludwig Schmidt -
2021 Spotlight: Outside the Echo Chamber: Optimizing the Performative Risk »
John Miller · Juan Perdomo · Tijana Zrnic -
2021 Spotlight: Alternative Microfoundations for Strategic Classification »
Meena Jagadeesan · Celestine Mendler-Dünner · Moritz Hardt -
2020 : Live Invited Talk: Alexi Efros "Imagining a Post-Dataset Era" »
Alexei Efros -
2020 Poster: Performative Prediction »
Juan Perdomo · Tijana Zrnic · Celestine Mendler-Dünner · Moritz Hardt -
2020 Poster: Strategic Classification is Causal Modeling in Disguise »
John Miller · Smitha Milli · Moritz Hardt -
2020 Poster: Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning »
Esther Rolf · Max Simchowitz · Sarah Dean · Lydia T. Liu · Daniel Bjorkegren · Moritz Hardt · Joshua Blumenstock -
2020 Poster: The Effect of Natural Distribution Shift on Question Answering Models »
John Miller · Karl Krauth · Benjamin Recht · Ludwig Schmidt -
2019 : Invited Talk by Professor Alexei Efros (UC Berkeley) »
Alexei Efros -
2019 Poster: Natural Analysts in Adaptive Data Analysis »
Tijana Zrnic · Moritz Hardt -
2019 Poster: The Implicit Fairness Criterion of Unconstrained Learning »
Lydia T. Liu · Max Simchowitz · Moritz Hardt -
2019 Oral: The Implicit Fairness Criterion of Unconstrained Learning »
Lydia T. Liu · Max Simchowitz · Moritz Hardt -
2019 Oral: Natural Analysts in Adaptive Data Analysis »
Tijana Zrnic · Moritz Hardt -
2018 Poster: CyCADA: Cycle-Consistent Adversarial Domain Adaptation »
Judy Hoffman · Eric Tzeng · Taesung Park · Jun-Yan Zhu · Philip Isola · Kate Saenko · Alexei Efros · Trevor Darrell -
2018 Oral: CyCADA: Cycle-Consistent Adversarial Domain Adaptation »
Judy Hoffman · Eric Tzeng · Taesung Park · Jun-Yan Zhu · Philip Isola · Kate Saenko · Alexei Efros · Trevor Darrell -
2018 Poster: Investigating Human Priors for Playing Video Games »
Rachit Dubey · Pulkit Agrawal · Deepak Pathak · Tom Griffiths · Alexei Efros -
2018 Poster: Delayed Impact of Fair Machine Learning »
Lydia T. Liu · Sarah Dean · Esther Rolf · Max Simchowitz · Moritz Hardt -
2018 Oral: Investigating Human Priors for Playing Video Games »
Rachit Dubey · Pulkit Agrawal · Deepak Pathak · Tom Griffiths · Alexei Efros -
2018 Oral: Delayed Impact of Fair Machine Learning »
Lydia T. Liu · Sarah Dean · Esther Rolf · Max Simchowitz · Moritz Hardt -
2017 Poster: Curiosity-driven Exploration by Self-supervised Prediction »
Deepak Pathak · Pulkit Agrawal · Alexei Efros · Trevor Darrell -
2017 Talk: Curiosity-driven Exploration by Self-supervised Prediction »
Deepak Pathak · Pulkit Agrawal · Alexei Efros · Trevor Darrell