WeShort: Out-of-distribution Detection With Weak Shortcut structure

TL;DR

WeShort is a simple post-hoc method that leverages residual structures in neural networks to effectively detect out-of-distribution data, improving safety in real-world applications.

Contribution

This paper introduces WeShort, a novel post-hoc technique utilizing residual structures for improved OOD detection across various architectures.

Findings

Achieves state-of-the-art FPR95 and AUROC on ImageNet OOD detection.

Compatible with different OOD detection scores and network architectures.

Effectively reduces neural network overconfidence on OOD data.

Abstract

Neural networks have achieved impressive performance for data in the distribution which is the same as the training set but can produce an overconfident incorrect result for the data these networks have never seen. Therefore, it is essential to detect whether inputs come from out-of-distribution(OOD) in order to guarantee the safety of neural networks deployed in the real world. In this paper, we propose a simple and effective post-hoc technique, WeShort, to reduce the overconfidence of neural networks on OOD data. Our method is inspired by the observation of the internal residual structure, which shows the separation of the OOD and in-distribution (ID) data in the shortcut layer. Our method is compatible with different OOD detection scores and can generalize well to different architectures of networks. We demonstrate our method on various OOD datasets to show its competitive performances and provide reasonable hypotheses to explain why our method works. On the ImageNet benchmark, Weshort achieves state-of-the-art performance on the false positive rate (FPR95) and the area under the receiver operating characteristic (AUROC) on the family of post-hoc methods.