Feature embedding-based methods have shown exceptional performance in detecting industrial anomalies by comparing features of target images with normal images. However, some methods do not meet the speed requirements of real-time inference, which is crucial for real-world applications. To address this issue, we propose a new method called Fast Adaptive Patch Memory (FAPM) for real-time industrial anomaly detection. FAPM utilizes patch-wise and layer-wise memory banks that store the embedding features of images at the patch and layer level, respectively, which eliminates unnecessary repetitive computations. We also propose patch-wise adaptive coreset sampling for faster and more accurate detection. FAPM performs well in both accuracy and speed compared to other state-of-the-art methods
@article{arxiv.2211.07381,
title = {FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection},
author = {Donghyeong Kim and Chaewon Park and Suhwan Cho and Sangyoun Lee},
journal= {arXiv preprint arXiv:2211.07381},
year = {2023}
}
Comments
Accepted to 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (2023 ICASSP)