Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation

TL;DR

This paper introduces a semi-orthogonal embedding technique that significantly improves the efficiency of unsupervised anomaly segmentation by reducing computational costs while maintaining state-of-the-art performance across multiple datasets.

Contribution

The authors propose a semi-orthogonal embedding method that generalizes random feature selection, enabling scalable and robust covariance inverse approximation in unsupervised anomaly segmentation.

Findings

Achieves state-of-the-art results on multiple datasets

Reduces computational cost cubically for covariance inverse

Provides theoretical and empirical validation of the approach

Abstract

We present the efficiency of semi-orthogonal embedding for unsupervised anomaly segmentation. The multi-scale features from pre-trained CNNs are recently used for the localized Mahalanobis distances with significant performance. However, the increased feature size is problematic to scale up to the bigger CNNs, since it requires the batch-inverse of multi-dimensional covariance tensor. Here, we generalize an ad-hoc method, random feature selection, into semi-orthogonal embedding for robust approximation, cubically reducing the computational cost for the inverse of multi-dimensional covariance tensor. With the scrutiny of ablation studies, the proposed method achieves a new state-of-the-art with significant margins for the MVTec AD, KolektorSDD, KolektorSDD2, and mSTC datasets. The theoretical and empirical analyses offer insights and verification of our straightforward yet cost-effective approach.