2000 character limit reached
Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation (2301.09602v2)
Published 23 Jan 2023 in cs.CV
Abstract: We propose an incremental improvement to Fully Convolutional Data Description (FCDD), an adaptation of the one-class classification approach from anomaly detection to image anomaly segmentation (a.k.a. anomaly localization). We analyze its original loss function and propose a substitute that better resembles its predecessor, the Hypersphere Classifier (HSC). Both are compared on the MVTec Anomaly Detection Dataset (MVTec-AD) -- training images are flawless objects/textures and the goal is to segment unseen defects -- showing that consistent improvement is achieved by better designing the pixel-wise supervision.
- “A Unifying Review of Deep and Shallow Anomaly Detection,” Proceedings of the IEEE, vol. 109, no. 5, pp. 756–795, 2021.
- “Deep Learning for Anomaly Detection: A Review,” ACM Comput. Surv., vol. 54, no. 2, Mar. 2021, Place: New York, NY, USA Publisher: Association for Computing Machinery.
- “The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection,” International Journal of Computer Vision, vol. 129, no. 4, pp. 1038–1059, Apr. 2021.
- “Explainable Deep One-Class Classification,” in International Conference on Learning Representations, 2021.
- “One-Class Classification: A Survey,” Tech. Rep. arXiv:2101.03064, arXiv, Jan. 2021, arXiv:2101.03064 [cs] type: article.
- “Estimating the Support of a High-Dimensional Distribution,” Neural Computation, vol. 13, no. 7, pp. 1443–1471, July 2001.
- “Support Vector Data Description,” Machine Learning, vol. 54, no. 1, pp. 45–66, Jan. 2004.
- “Deep One-Class Classification,” in Proceedings of the 35th International Conference on Machine Learning, Jennifer Dy and Andreas Krause, Eds. July 2018, vol. 80 of Proceedings of Machine Learning Research, pp. 4393–4402, PMLR.
- “Deep Semi-Supervised Anomaly Detection,” arXiv:1906.02694 [cs, stat], Feb. 2020, arXiv: 1906.02694.
- “Rethinking Assumptions in Deep Anomaly Detection,” arXiv:2006.00339 [cs, stat], July 2021, arXiv: 2006.00339.
- “DRAEM - A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 8330–8339.
- “Sub-Image Anomaly Detection with Deep Pyramid Correspondences,” 2020.
- “Towards Total Recall in Industrial Anomaly Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022, pp. 14318–14328.
- “Gaussian Anomaly Detection by Modeling the Distribution of Normal Data in Pretrained Deep Features,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–13, 2021, Conference Name: IEEE Transactions on Instrumentation and Measurement.
- “PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization,” in Pattern Recognition. ICPR International Workshops and Challenges, Alberto Del Bimbo, Rita Cucchiara, Stan Sclaroff, Giovanni Maria Farinella, Tao Mei, Marco Bertini, Hugo Jair Escalante, and Roberto Vezzani, Eds., Cham, 2021, pp. 475–489, Springer International Publishing.
- “N-pad : Neighboring Pixel-based Industrial Anomaly Detection,” Oct. 2022, 0 citations (Semantic Scholar/arXiv) [2022-10-25] 0 citations (Semantic Scholar/DOI) [2022-10-25] arXiv:2210.08768 [cs].
- “Image Anomaly Detection and Localization with Position and Neighborhood Information,” Nov. 2022, 0 citations (Semantic Scholar/arXiv) [2022-11-28] arXiv:2211.12634 [cs].
- “AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection,” Oct. 2022, 0 citations (Semantic Scholar/arXiv) [2022-11-01] arXiv:2210.14913 [cs] version: 1.