Unsupervised Anomaly Detection with an Enhanced Teacher for Student-Teacher Feature Pyramid Matching

TL;DR

This paper introduces ET-STPM, a student-teacher framework with an enhanced teacher network for improved unsupervised anomaly detection, achieving state-of-the-art accuracy on image and pixel levels.

Contribution

It proposes an enhanced teacher network within a student-teacher framework for anomaly detection, pre-trained on ImageNet and fine-tuned on MVTech-AD, leading to superior performance.

Findings

Achieved 0.971 mean accuracy on image-level detection.

Achieved 0.977 mean accuracy on pixel-level detection.

Outperformed previous methods in anomaly detection metrics.

Abstract

Anomaly detection or outlier is one of the challenging subjects in unsupervised learning . This paper is introduced a student-teacher framework for anomaly detection that its teacher network is enhanced for achieving high-performance metrics . For this purpose , we first pre-train the ResNet-18 network on the ImageNet and then fine-tune it on the MVTech-AD dataset . Experiment results on the image-level and pixel-level demonstrate that this idea has achieved better metrics than the previous methods . Our model , Enhanced Teacher for Student-Teacher Feature Pyramid (ET-STPM), achieved 0.971 mean accuracy on the image-level and 0.977 mean accuracy on the pixel-level for anomaly detection.