Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy

TL;DR

This paper introduces SNoJoE, a spectral normalized joint energy method for multi-label out-of-distribution detection, significantly improving detection performance and setting new state-of-the-art results.

Contribution

The paper proposes a novel spectral normalized joint energy approach for multi-label OOD detection, addressing the limited research in this area and enhancing robustness and efficacy.

Findings

Achieves 11% and 54% relative reductions in FPR95 on OOD datasets.

Outperforms previous methods in multi-label OOD detection.

Demonstrates the effectiveness of spectral normalization in this context.

Abstract

In today's interconnected world, achieving reliable out-of-distribution (OOD) detection poses a significant challenge for machine learning models. While numerous studies have introduced improved approaches for multi-class OOD detection tasks, the investigation into multi-label OOD detection tasks has been notably limited. We introduce Spectral Normalized Joint Energy (SNoJoE), a method that consolidates label-specific information across multiple labels through the theoretically justified concept of an energy-based function. Throughout the training process, we employ spectral normalization to manage the model's feature space, thereby enhancing model efficacy and generalization, in addition to bolstering robustness. Our findings indicate that the application of spectral normalization to joint energy scores notably amplifies the model's capability for OOD detection. We perform OOD detection experiments utilizing PASCAL-VOC as the in-distribution dataset and ImageNet-22K or Texture as the out-of-distribution datasets. Our experimental results reveal that, in comparison to prior top performances, SNoJoE achieves 11% and 54% relative reductions in FPR95 on the respective OOD datasets, thereby defining the new state of the art in this field of study.