Timezone: »

Training OOD Detectors in their Natural Habitats
Julian Katz-Samuels · Julia Nakhleh · Robert Nowak · Sharon Li

Wed Jul 20 01:45 PM -- 01:50 PM (PDT) @ Room 301 - 303

Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild. Recent methods use auxiliary outlier data to regularize the model for improved OOD detection. However, these approaches make a strong distributional assumption that the auxiliary outlier data is completely separable from the in-distribution (ID) data. In this paper, we propose a novel framework that leverages wild mixture data---that naturally consists of both ID and OOD samples. Such wild data is abundant and arises freely upon deploying a machine learning classifier in their natural habitats. Our key idea is to formulate a constrained optimization problem and to show how to tractably solve it. Our learning objective maximizes the OOD detection rate, subject to constraints on the classification error of ID data and on the OOD error rate of ID examples. We extensively evaluate our approach on common OOD detection tasks and demonstrate superior performance. Code is available at https://github.com/jkatzsam/woods_ood.

Author Information

Julian Katz-Samuels (University of Wisconsin)
Julia Nakhleh (University of Wisconsin-Madison)
Robert Nowak (University of Wisconsion-Madison)
Robert Nowak

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.

Sharon Li (University of Wisconsin-Madison)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors