Timezone: »

Can multi-label classification networks know what they don’t know?
Haoran Wang · Weitang Liu · Alex Bocchieri · Yixuan Li

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @

Estimating out-of-distribution (OOD) uncertainty is a major challenge for safely deploying machine learning models in the open-world environment. 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 JointEnergy, a simple and effective method, which estimates the OOD indicator scores by aggregating label-wise energy scores from multiple labels. We show that JointEnergy 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 JointEnergy can reduce the FPR95 by up to 10.05% compared to the previous best baseline, establishing state-of-the-art performance.

Author Information

Haoran Wang (Carnegie Mellon University)
Weitang Liu (UC San Diego)
Alex Bocchieri (University of Wisconsin, Madison)
Yixuan Li (University of Wisconsin-Madison)

More from the Same Authors