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

We present the efficiency of semi-orthogonal embedding for unsupervisedanomaly segmentation. The multi-scale features from pre-trained CNNs arerecently used for the localized Mahalanobis distances with significantperformance. However, the increased feature size is problematic to scale up tothe bigger CNNs, since it requires the batch-inverse of multi-dimensionalcovariance tensor. Here, we generalize an ad-hoc method, random featureselection, into semi-orthogonal embedding for robust approximation, cubicallyreducing the computational cost for the inverse of multi-dimensional covariancetensor. With the scrutiny of ablation studies, the proposed method achieves anew state-of-the-art with significant margins for the MVTec AD, KolektorSDD,KolektorSDD2, and mSTC datasets. The theoretical and empirical analyses offerinsights and verification of our straightforward yet cost-effective approach.

Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation