articleIEEE AccessJan 1, 2022GOLD OA

CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization

SLSungwook LeeSLSeunghyun LeeBCByung Cheol Song

Inha University

Indexed incrossrefdoaj

Abstract

For a long time, anomaly localization has been widely used in industries. Previous studies focused on approximating the distribution of normal features without adaptation to a target dataset. However, since anomaly localization should precisely discriminate normal and abnormal features, the absence of adaptation may make the normality of abnormal features overestimated. Thus, we propose Coupled-hypersphere-based Feature Adaptation (CFA) which accomplishes sophisticated anomaly localization using features adapted to the target dataset. CFA consists of (1) a learnable patch descriptor that learns and embeds target-oriented features and (2) scalable memory bank independent of the size of the target dataset. And,…

Citation impact

283
total citations
FWCI
35.93
Percentile
100%
References
32
Citations per year

Authors

3

Topics & keywords

Topics
Keywords
  • Hypersphere
  • Anomaly detection
  • Computer science
  • Pattern recognition (psychology)
  • Artificial intelligence
  • Anomaly (physics)
  • Benchmark (surveying)
  • Feature (linguistics)
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.

Funding