Multi-label out-of-distribution detection via evidential learning

TL;DR

This paper introduces a novel evidential deep learning approach with a CNN architecture for multi-label out-of-distribution detection in visual recognition, demonstrating superior performance over existing methods.

Contribution

It proposes a Beta Evidential Neural Network and two new uncertainty-based scores for multi-label OOD detection, advancing robustness in visual recognition tasks.

Findings

Outperforms several state-of-the-art methods on PASCAL-VOC, MS-COCO, and NUS-WIDE datasets.

Effective in detecting multi-label out-of-distribution data.

Provides reliable uncertainty estimates for OOD samples.

Abstract

A crucial requirement for machine learning algorithms is not only to perform well, but also to show robustness and adaptability when encountering novel scenarios. One way to achieve these characteristics is to endow the deep learning models with the ability to detect out-of-distribution (OOD) data, i.e. data that belong to distributions different from the one used during their training. It is even a more complicated situation, when these data usually are multi-label. In this paper, we propose an approach based on evidential deep learning in order to meet these challenges applied to visual recognition problems. More concretely, we designed a CNN architecture that uses a Beta Evidential Neural Network to compute both the likelihood and the predictive uncertainty of the samples. Based on these results, we propose afterwards two new uncertainty-based scores for OOD data detection: (i) OOD - score Max, based on the maximum evidence; and (ii) OOD score - Sum, which considers the evidence from all outputs. Extensive experiments have been carried out to validate the proposed approach using three widely-used datasets: PASCAL-VOC, MS-COCO and NUS-WIDE, demonstrating its outperformance over several State-of-the-Art methods.