English

Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation

Computer Vision and Pattern Recognition 2023-12-05 v2

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.

Keywords

Cite

@article{arxiv.2301.09602,
  title  = {Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation},
  author = {Joao P. C. Bertoldo and Santiago Velasco-Forero and Jesus Angulo and Etienne Decencière},
  journal= {arXiv preprint arXiv:2301.09602},
  year   = {2023}
}

Comments

Submitted to the 2023 IEEE International Conference on Image Processing (ICIP 2023)

R2 v1 2026-06-28T08:18:02.647Z