Attention Modules Improve Modern Image-Level Anomaly Detection: A DifferNet Case Study

TL;DR

This paper introduces AttentDifferNet, an enhanced DifferNet model with attention modules, significantly improving anomaly detection accuracy on multiple datasets in visual inspection tasks.

Contribution

It presents a novel attention-augmented DifferNet model that outperforms existing methods in unsupervised visual anomaly detection.

Findings

Achieves higher AUC scores across datasets

Demonstrates the effectiveness of attention modules in anomaly detection

Establishes a new baseline emphasizing attention's importance

Abstract

Within (semi-)automated visual inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery. The emergence of these often rarely occurring defect patterns explains the general need for labeled data corpora. To not only alleviate this issue but to furthermore advance the current state of the art in unsupervised visual inspection, this contribution proposes a DifferNet-based solution enhanced with attention modules utilizing SENet and CBAM as backbone - AttentDifferNet - to improve the detection and classification capabilities on three different visual inspection and anomaly detection datasets: MVTec AD, InsPLAD-fault, and Semiconductor Wafer. In comparison to the current state of the art, it is shown that AttentDifferNet achieves improved results, which are, in turn, highlighted throughout our quantitative as well as qualitative evaluation, indicated by a general improvement in AUC of 94.34 vs. 92.46, 96.67 vs. 94.69, and 90.20 vs. 88.74%. As our variants to AttentDifferNet show great prospects in the context of currently investigated approaches, a baseline is formulated, emphasizing the importance of attention for anomaly detection.