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

Unsupervised anomaly localization, which plays a critical role in industrialmanufacturing, is to identify anomalous regions that deviate from patternsestablished exclusively from nominal samples. Recent mainstream methods focuson approximating the target feature distribution by leveraging embeddings fromImageNet models. However, a common issue in many anomaly localization methodsis the lack of adaptability of the feature approximations to specific targets.Consequently, their ability to effectively identify anomalous regions reliessignificantly on the data coverage provided by the finite resources in a memorybank. In this paper, we propose a novel subspace-aware feature reconstructionframework for anomaly localization. To achieve adaptive feature approximation,our proposed method involves the reconstruction of the feature representationthrough the self-expressive model designed to learn low-dimensional subspaces.Importantly, the sparsity of the subspace representation contributes tocovering feature patterns from the same subspace with fewer resources, leadingto a reduction in the memory bank. Extensive experiments across threeindustrial benchmark datasets demonstrate that our approach achievescompetitive anomaly localization performance compared to state-of-the-artmethods by adaptively reconstructing target features with a small number ofsamples.

Subspace-Aware Feature Reconstruction for Unsupervised Anomaly Localization