Timezone: »

Concept-based Explanations for Out-of-Distribution Detectors
Jihye Choi · Jayaram Raghuram · Ryan Feng · Jiefeng Chen · Somesh Jha · Atul Prakash

Wed Jul 26 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #442

Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improving the performance of OOD detectors, a critical gap remains in interpreting their decisions. We help bridge this gap by providing explanations for OOD detectors based on learned high-level concepts. We first propose two new metrics for assessing the effectiveness of a particular set of concepts for explaining OOD detectors: 1) detection completeness, which quantifies the sufficiency of concepts for explaining an OOD-detector's decisions, and 2) concept separability, which captures the distributional separation between in-distribution and OOD data in the concept space. Based on these metrics, we propose an unsupervised framework for learning a set of concepts that satisfy the desired properties of high detection completeness and concept separability, and demonstrate its effectiveness in providing concept-based explanations for diverse off-the-shelf OOD detectors. We also show how to identify prominent concepts contributing to the detection results, and provide further reasoning about their decisions.

Author Information

Jihye Choi (University of Wisconsin-Madison)
Jayaram Raghuram (University of Wisconsin, Madison)
Ryan Feng (University of Michigan)
Jiefeng Chen (University of Wisconsin-Madison)
Somesh Jha (University of Wisconsin, Madison)
Atul Prakash (University of Michigan, Ann Arbor)

More from the Same Authors