Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detection

TL;DR

This paper introduces Attention Fusion Reverse Distillation (AFRD), a novel method for multi-lighting image anomaly detection that leverages a teacher-student framework with attention-based feature fusion to improve detection accuracy.

Contribution

The paper proposes AFRD, a new approach that effectively handles multiple lighting inputs in anomaly detection using attention fusion and reverse distillation, outperforming existing methods.

Findings

AFRD achieves superior performance on Eyecandies dataset.

Using multiple lighting conditions improves anomaly detection accuracy.

Attention fusion effectively aggregates multi-lighting features.

Abstract

This study targets Multi-Lighting Image Anomaly Detection (MLIAD), where multiple lighting conditions are utilized to enhance imaging quality and anomaly detection performance. While numerous image anomaly detection methods have been proposed, they lack the capacity to handle multiple inputs for a single sample, like multi-lighting images in MLIAD. Hence, this study proposes Attention Fusion Reverse Distillation (AFRD) to handle multiple inputs in MLIAD. For this purpose, AFRD utilizes a pre-trained teacher network to extract features from multiple inputs. Then these features are aggregated into fused features through an attention module. Subsequently, a corresponding student net-work is utilized to regress the attention fused features. The regression errors are denoted as anomaly scores during inference. Experiments on Eyecandies demonstrates that AFRD achieves superior MLIAD performance than other MLIAD alternatives, also highlighting the benefit of using multiple lighting conditions for anomaly detection.