Attention Modules Improve Modern Image-Level Anomaly Detection: A DifferNet Case Study
This work addresses visual inspection for industrial quality control, offering an incremental improvement over existing methods.
The authors tackled the problem of detecting small visual defects in high-resolution images by enhancing DifferNet with attention modules (SENet and CBAM), achieving improved AUC scores on three datasets: 94.34% vs. 92.46%, 96.67% vs. 94.69%, and 90.20% vs. 88.74%.
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.