English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

For a long time, anomaly localization has been widely used in industries.Previous studies focused on approximating the distribution of normal featureswithout adaptation to a target dataset. However, since anomaly localizationshould precisely discriminate normal and abnormal features, the absence ofadaptation may make the normality of abnormal features overestimated. Thus, wepropose Coupled-hypersphere-based Feature Adaptation (CFA) which accomplishessophisticated anomaly localization using features adapted to the targetdataset. CFA consists of (1) a learnable patch descriptor that learns andembeds target-oriented features and (2) scalable memory bank independent of thesize of the target dataset. And, CFA adopts transfer learning to increase thenormal feature density so that abnormal features can be clearly distinguishedby applying patch descriptor and memory bank to a pre-trained CNN. The proposedmethod outperforms the previous methods quantitatively and qualitatively. Forexample, it provides an AUROC score of 99.5% in anomaly detection and 98.5% inanomaly localization of MVTec AD benchmark. In addition, this paper points outthe negative effects of biased features of pre-trained CNNs and emphasizes theimportance of the adaptation to the target dataset. The code is publiclyavailable at https://github.com/sungwool/CFA_for_anomaly_localization.

CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization