“Classifying Texture Anomalies at First Sight” by Ardelean and Weyrich
Conference:
Type(s):
Title:
- Classifying Texture Anomalies at First Sight
Session/Category Title: Images, Video & Computer Vision
Presenter(s)/Author(s):
Abstract:
This poster summarizes our recent line of research on localization and classification of anomalies in real-world texture images. It presents our novel method for zero-shot anomaly localization (FCA), its extension to leverage contaminated data, and anomaly clustering through contrastive learning.
References:
[1]
Toshimichi Aota, Lloyd Teh Tzer Tong, and Takayuki Okatani. 2023. Zero-Shot Versus Many-Shot: Unsupervised Texture Anomaly Detection. In IEEE/CVF Winter Conference on Applications of Computer Vision.
[2]
Andrei-Timotei Ardelean and Tim Weyrich. 2024a. Blind Localization and Clustering of Anomalies in Textures. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.
[3]
Andrei-Timotei Ardelean and Tim Weyrich. 2024b. High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis. In IEEE/CVF Winter Conference on Applications of Computer Vision.
[4]
Ariel Elnekave and Yair Weiss. 2022. Generating natural images with direct Patch Distributions Matching. In European Conference on Computer Vision.
[5]
R. Hadsell, S. Chopra, and Y. LeCun. 2006. Dimensionality Reduction by Learning an Invariant Mapping. In IEEE/CVF Conference on Computer Vision and Pattern Recognition.
[6]
Joep Moritz, Stuart James, Tom S.F. Haines, Tobias Ritschel, and Tim Weyrich. 2017. Texture Stationarization: Turning Photos into Tileable Textures. Computer Graphics Forum (Proc. Eurographics) (2017).
[7]
Kihyuk Sohn, Jinsung Yoon, Chun-Liang Li, Chen-Yu Lee, and Tomas Pfister. 2023. Anomaly clustering: Grouping images into coherent clusters of anomaly types. In IEEE/CVF Winter Conference on Applications of Computer Vision.
