Poster

OpenMix: Exploring Outlier Samples for Misclassification Detection

Fei Zhu · Zhen Cheng · Xu-Yao Zhang · Cheng-Lin Liu

West Building Exhibit Halls ABC 367
award Highlight
[ ] [ Project Page ]
[ Paper PDF [ Slides [ Poster

Abstract:

Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications. Unfortunately, modern deep neural networks are often overconfident for their erroneous predictions. In this work, we exploit the easily available outlier samples, i.e., unlabeled samples coming from non-target classes, for helping detect misclassification errors. Particularly, we find that the well-known Outlier Exposure, which is powerful in detecting out-of-distribution (OOD) samples from unknown classes, does not provide any gain in identifying misclassification errors. Based on these observations, we propose a novel method called OpenMix, which incorporates open-world knowledge by learning to reject uncertain pseudo-samples generated via outlier transformation. OpenMix significantly improves confidence reliability under various scenarios, establishing a strong and unified framework for detecting both misclassified samples from known classes and OOD samples from unknown classes.

Chat is not available.