Neural Architecture Search for Visual Anomaly Segmentation

Tommie Kerssies, Joaquin Vanschoren
Proceedings of the Second International Conference on Automated Machine Learning, PMLR 224:20/1-14, 2023.

Abstract

This paper presents the first application of neural architecture search to the complex task of segmenting visual anomalies. Measurement of anomaly segmentation performance is challenging due to imbalanced anomaly pixels, varying region areas, and various types of anomalies. First, the region-weighted Average Precision (rwAP) metric is proposed as an alternative to existing metrics, which does not need to be limited to a specific maximum false positive rate. Second, the AutoPatch neural architecture search method is proposed, which enables efficient segmentation of visual anomalies without any training. By leveraging a pre-trained supernet, a black-box optimization algorithm can directly minimize computational complexity and maximize performance on a small validation set of anomalous examples. Finally, compelling results are presented on the widely studied MVTec dataset, demonstrating that AutoPatch outperforms the current state-of-the-art with lower computational complexity, using only one example per type of anomaly. The results highlight the potential of automated machine learning to optimize throughput in industrial quality control. The code for AutoPatch is available at: \url{https://github.com/tommiekerssies/AutoPatch}.

Cite this Paper

BibTeX
@InProceedings{pmlr-v224-kerssies23a, title = {Neural Architecture Search for Visual Anomaly Segmentation}, author = {Kerssies, Tommie and Vanschoren, Joaquin}, booktitle = {Proceedings of the Second International Conference on Automated Machine Learning}, pages = {20/1--14}, year = {2023}, editor = {Faust, Aleksandra and Garnett, Roman and White, Colin and Hutter, Frank and Gardner, Jacob R.}, volume = {224}, series = {Proceedings of Machine Learning Research}, month = {12--15 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v224/kerssies23a/kerssies23a.pdf}, url = {https://proceedings.mlr.press/v224/kerssies23a.html}, abstract = {This paper presents the first application of neural architecture search to the complex task of segmenting visual anomalies. Measurement of anomaly segmentation performance is challenging due to imbalanced anomaly pixels, varying region areas, and various types of anomalies. First, the region-weighted Average Precision (rwAP) metric is proposed as an alternative to existing metrics, which does not need to be limited to a specific maximum false positive rate. Second, the AutoPatch neural architecture search method is proposed, which enables efficient segmentation of visual anomalies without any training. By leveraging a pre-trained supernet, a black-box optimization algorithm can directly minimize computational complexity and maximize performance on a small validation set of anomalous examples. Finally, compelling results are presented on the widely studied MVTec dataset, demonstrating that AutoPatch outperforms the current state-of-the-art with lower computational complexity, using only one example per type of anomaly. The results highlight the potential of automated machine learning to optimize throughput in industrial quality control. The code for AutoPatch is available at: \url{https://github.com/tommiekerssies/AutoPatch}.} }
Endnote
%0 Conference Paper %T Neural Architecture Search for Visual Anomaly Segmentation %A Tommie Kerssies %A Joaquin Vanschoren %B Proceedings of the Second International Conference on Automated Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Aleksandra Faust %E Roman Garnett %E Colin White %E Frank Hutter %E Jacob R. Gardner %F pmlr-v224-kerssies23a %I PMLR %P 20/1--14 %U https://proceedings.mlr.press/v224/kerssies23a.html %V 224 %X This paper presents the first application of neural architecture search to the complex task of segmenting visual anomalies. Measurement of anomaly segmentation performance is challenging due to imbalanced anomaly pixels, varying region areas, and various types of anomalies. First, the region-weighted Average Precision (rwAP) metric is proposed as an alternative to existing metrics, which does not need to be limited to a specific maximum false positive rate. Second, the AutoPatch neural architecture search method is proposed, which enables efficient segmentation of visual anomalies without any training. By leveraging a pre-trained supernet, a black-box optimization algorithm can directly minimize computational complexity and maximize performance on a small validation set of anomalous examples. Finally, compelling results are presented on the widely studied MVTec dataset, demonstrating that AutoPatch outperforms the current state-of-the-art with lower computational complexity, using only one example per type of anomaly. The results highlight the potential of automated machine learning to optimize throughput in industrial quality control. The code for AutoPatch is available at: \url{https://github.com/tommiekerssies/AutoPatch}.
APA
Kerssies, T. & Vanschoren, J.. (2023). Neural Architecture Search for Visual Anomaly Segmentation. Proceedings of the Second International Conference on Automated Machine Learning, in Proceedings of Machine Learning Research 224:20/1-14 Available from https://proceedings.mlr.press/v224/kerssies23a.html.

Related Material