ICML 2023

Timezone: »

Poster

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection

Haoyue Bai · Gregory Canal · Xuefeng Du · Jeongyeol Kwon · Robert Nowak · Sharon Li

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #203

in Poster Session 2 »

Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OOD detection respectively. While both problems have received significant research attention lately, they have been pursued independently. This may not be surprising, since the two tasks have seemingly conflicting goals. This paper provides a new unified approach that is capable of simultaneously generalizing to covariate shifts while robustly detecting semantic shifts. We propose a margin-based learning framework that exploits freely available unlabeled data in the wild that captures the environmental test-time OOD distributions under both covariate and semantic shifts. We show both empirically and theoretically that the proposed margin constraint is the key to achieving both OOD generalization and detection. Extensive experiments show the superiority of our framework, outperforming competitive baselines that specialize in either OOD generalization or OOD detection. Code is publicly available at https://github.com/deeplearning-wisc/scone.

[ PDF] [ Poster]

Author Information

Haoyue Bai (University of Wisconsin - Madison)

Gregory Canal (University of Wisconsin-Madison)

Xuefeng Du (University of Wisconsin, Madison)

Jeongyeol Kwon (University of Wisconsin-Madison)

I am currently a PostDoc at University of Wisconsin-Madison, working with Prof. Robert Nowak. Prior to joining UW-Madison, I received my Ph.D. in ECE department at UT Austin, where I had wonderful years of learning and working with my advisor Prof. Constantine Caramanis. I got my Bachelor’s Degree in Electrical and Computer Engineering from Seoul National University (SNU) in 2016.

Robert Nowak (University of Wisconsion-Madison)

Robert Nowak holds the Nosbusch Professorship in Engineering at the University of Wisconsin-Madison, where his research focuses on signal processing, machine learning, optimization, and statistics.