Blind Localization and Clustering of Anomalies in Textures

Abstract

Anomaly detection and localization in images is a growing field in computer vision. In this area, a seemingly understudied problem is anomaly clustering, i.e., identifying and grouping different types of anomalies in a fully unsupervised manner. In this work, we propose a novel method for clustering anomalies in largely stationary images (textures) in a blind setting. That is, the input consists of normal and anomalous images without distinction and without labels. What contributes to the difficulty of the task is that anomalous regions are often small and may present only subtle changes in appearance, which can be easily overshadowed by the genuine variance in the texture. Moreover, each anomaly type may have a complex appearance distribution. We introduce a novel scheme for solving this task using a combination of blind anomaly localization and contrastive learning. By identifying the anomalous regions with high fidelity, we can restrict our focus to those regions of interest; then, contrastive learning is employed to increase the separability of different anomaly types and reduce the intra-class variation. Our experiments show that the proposed solution yields significantly better results compared to prior work, setting a new state of the art.

Citation Style:    Display Alpha ACM SIGGRAPH IEEEtran Publication

Blind Localization and Clustering of Anomalies in Textures. Andrei-Timotei Ardelean, Tim Weyrich. Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, to appear, June 2024.Andrei-Timotei Ardelean and Tim Weyrich. Blind localization and clustering of anomalies in textures. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, June 2024.Ardelean, A.-T., and Weyrich, T. 2024. Blind localization and clustering of anomalies in textures. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.A.-T. Ardelean and T. Weyrich, “Blind localization and clustering of anomalies in textures,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Jun. 2024. PDF (6 MB) Suppl. Material (461 KB) Source Code BibTeX arXiv Version

Related Publications

Classifying Texture Anomalies at First Sight. Andrei-Timotei Ardelean, Tim Weyrich. ACM SIGGRAPH Posters '24, July 27–August 01, Denver, CO, USA, 2024.Andrei-Timotei Ardelean and Tim Weyrich. Classifying texture anomalies at first sight. In ACM SIGGRAPH 2024 Posters, SIGGRAPH ’24, New York, NY, USA, July 2024. Association for Computing Machinery.Ardelean, A.-T., and Weyrich, T. 2024. Classifying texture anomalies at first sight. In ACM SIGGRAPH 2024 Posters, Association for Computing Machinery, New York, NY, USA, SIGGRAPH ’24.A.-T. Ardelean and T. Weyrich, “Classifying texture anomalies at first sight,” in ACM SIGGRAPH 2024 Posters, ser. SIGGRAPH ’24. New York, NY, USA: Association for Computing Machinery, Jul. 2024. [Online]. Available: https://doi.org/10.1145/3641234.3671071 [Web Page][PDF (3.0 MB)][Poster PDF (16 MB)][BibTeX]

High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis. Andrei-Timotei Ardelean, Tim Weyrich. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 1134–1144, January 2024.Andrei-Timotei Ardelean and Tim Weyrich. High-fidelity zero-shot texture anomaly localization using feature correspondence analysis. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2024.Ardelean, A.-T., and Weyrich, T. 2024. High-fidelity zero-shot texture anomaly localization using feature correspondence analysis. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).A.-T. Ardelean and T. Weyrich, “High-fidelity zero-shot texture anomaly localization using feature correspondence analysis,” in Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan. 2024. [Web Page][PDF (37 MB)][Low-res PDF (2.0 MB)][Suppl. Material, PDF only (1.4 MB)][Suppl. Material, Full Archive (90 MB)][Short Video (55 MB)][Source Code][BibTeX][arXiv Versions][Open-Access Version]

Acknowledgments

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 956585 (PRIME ITN).