Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection

TL;DR

This paper introduces DMDD, a novel unsupervised anomaly detection method using dual-modeling decouple distillation with a decouple student-teacher network, improving localization accuracy by focusing on anomaly edges and centers.

Contribution

The paper proposes a dual-modeling decouple distillation framework that decouples normal and abnormal features, enhancing anomaly detection and localization in unsupervised settings.

Findings

Achieves 98.85% pixel-level AUC on MVTec AD

Surpasses previous state-of-the-art in anomaly localization

Effectively focuses on both anomaly edges and centers

Abstract

Knowledge distillation based on student-teacher network is one of the mainstream solution paradigms for the challenging unsupervised Anomaly Detection task, utilizing the difference in representation capabilities of the teacher and student networks to implement anomaly localization. However, over-generalization of the student network to the teacher network may lead to negligible differences in representation capabilities of anomaly, thus affecting the detection effectiveness. Existing methods address the possible over-generalization by using differentiated students and teachers from the structural perspective or explicitly expanding distilled information from the content perspective, which inevitably result in an increased likelihood of underfitting of the student network and poor anomaly detection capabilities in anomaly center or edge. In this paper, we propose Dual-Modeling Decouple Distillation (DMDD) for the unsupervised anomaly detection. In DMDD, a Decouple Student-Teacher Network is proposed to decouple the initial student features into normality and abnormality features. We further introduce Dual-Modeling Distillation based on normal-anomaly image pairs, fitting normality features of anomalous image and the teacher features of the corresponding normal image, widening the distance between abnormality features and the teacher features in anomalous regions. Synthesizing these two distillation ideas, we achieve anomaly detection which focuses on both edge and center of anomaly. Finally, a Multi-perception Segmentation Network is proposed to achieve focused anomaly map fusion based on multiple attention. Experimental results on MVTec AD show that DMDD surpasses SOTA localization performance of previous knowledge distillation-based methods, reaching 98.85% on pixel-level AUC and 96.13% on PRO.