Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

TL;DR

This paper introduces class-aware contrastive learning to improve multi-class anomaly detection by reducing inter-class confusion and enhancing feature representations, leading to better performance across multiple datasets.

Contribution

The paper proposes a novel class-aware contrastive learning method that leverages category labels to improve multi-class anomaly detection, addressing performance degradation in existing methods.

Findings

Significant performance improvements over state-of-the-art methods.

Effective use of pseudo-class labels achieves comparable results.

Validated across five diverse datasets.

Abstract

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single model capable of handling multiple classes. However, directly extending early AD methods to multi-class settings often results in degraded performance. In this paper, we investigate this performance degradation observed in reconstruction-based methods, identifying the key issue: inter-class confusion. This confusion emerges when a model trained in multi-class scenarios incorrectly reconstructs samples from one class as those of another, thereby exacerbating reconstruction errors. To this end, we propose a simple yet effective modification, called class-aware contrastive learning (CCL). By explicitly leveraging raw object category information (\eg carpet or wood) as supervised signals, we introduce local CL to refine multiscale dense features, and global CL to obtain more compact feature representations of normal patterns, thereby effectively adapting the models to multi-class settings. Experiments across five datasets validate the effectiveness of our approach, demonstrating significant improvements and superior performance compared to state-of-the-art methods. Notably, ablation studies indicate that pseudo-class labels can achieve comparable performance.