High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis
Ardelean AT, Weyrich T (2024)
Publication Language: English
Publication Type: Conference contribution, Original article
Publication year: 2024
Pages Range: 1134-1144
Conference Proceedings Title: Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Event location: Waikoloa, Hawaii
URI: https://reality.tf.fau.de/pub/ardelean2024highfidelity.html
Abstract
We propose a novel method for Zero-Shot Anomaly Localization on textures. The task refers to identifying abnormal regions in an otherwise homogeneous image. To obtain a high-fidelity localization, we leverage a bijective mapping derived from the 1-dimensional Wasserstein Distance. As opposed to using holistic distances between distributions, the proposed approach allows pinpointing the non-conformity of a pixel in a local context with increased precision. By aggregating the contribution of the pixel to the errors of all nearby patches, we obtain a reliable anomaly score estimate. We validate our solution on several datasets and obtain more than a 40% reduction in error over the previous state of the art on the MVTec AD dataset in a zero-shot setting.
Authors with CRIS profile
Andrei-Timotei Ardelean
Lehrstuhl für Informatik 15 (Digital Reality)
Tim Weyrich
Lehrstuhl für Informatik 15 (Digital Reality)
How to cite
APA:
Ardelean, A.-T., & 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) (pp. 1134-1144). Waikoloa, Hawaii, US.
MLA:
Ardelean, Andrei-Timotei, and Tim Weyrich. "High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii 2024. 1134-1144.
BibTeX: Download