Energy-based Out-of-distribution Detection for Multi-label Classification

Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Abstract: Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from causing a model to fail during deployment. Improved methods for OOD detection in multi-class classification have emerged, while OOD detection methods for multi-label classification remain underexplored and use rudimentary techniques. We propose SumEnergy, a simple and effective method, which estimates the OOD indicator scores by aggregating energy scores from multiple labels. We show that SumEnergy can be mathematically interpreted from a joint likelihood perspective. Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels. We demonstrate the effectiveness of our method on three common multi-label classification benchmarks, including MS-COCO, PASCAL-VOC, and NUS-WIDE. We show that SumEnergy reduces the FPR95 by up to 10.05% compared to the previous best baseline, establishing state-of-the-art performance.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We investigate OOD detection for multi-label classification networks, and propose an energy-based method which is both theoretically meaningful and empirically effective, establishing state-of-the-art performance on common benchmarks.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=E_wyW6kc_B