Teacher Encoder-Student Decoder Denoising Guided Segmentation Network for Anomaly Detection

TL;DR

The paper introduces PFADSeg, a novel anomaly detection framework combining a teacher-student model with multi-scale feature fusion and denoising, achieving state-of-the-art results on the MVTec AD dataset.

Contribution

It proposes a unified teacher-encoder and student-decoder denoising model with adaptive feature fusion for improved anomaly segmentation.

Findings

Achieves 98.9% image-level AUC on MVTec AD

Attains 76.4% pixel-level mean precision

Reaches 78.7% instance-level mean precision

Abstract

Visual anomaly detection is a highly challenging task, often categorized as a one-class classification and segmentation problem. Recent studies have demonstrated that the student-teacher (S-T) framework effectively addresses this challenge. However, most S-T frameworks rely solely on pre-trained teacher networks to guide student networks in learning multi-scale similar features, overlooking the potential of the student networks to enhance learning through multi-scale feature fusion. In this study, we propose a novel model named PFADSeg, which integrates a pre-trained teacher network, a denoising student network with multi-scale feature fusion, and a guided anomaly segmentation network into a unified framework. By adopting a unique teacher-encoder and student-decoder denoising mode, the model improves the student network's ability to learn from teacher network features. Furthermore, an adaptive feature fusion mechanism is introduced to train a self-supervised segmentation network that synthesizes anomaly masks autonomously, significantly increasing detection performance. Rigorous evaluations on the widely-used MVTec AD dataset demonstrate that PFADSeg exhibits excellent performance, achieving an image-level AUC of 98.9%, a pixel-level mean precision of 76.4%, and an instance-level mean precision of 78.7%.