Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation

31 May 2021  ·  Jin-Hwa Kim, Do-Hyeong Kim, Saehoon Yi, Taehoon Lee ·

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.

PDF Abstract

Results from the Paper

 Ranked #1 on Unsupervised Anomaly Detection on KolektorSDD2 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Unsupervised Anomaly Detection KolektorSDD Semi-orthogonal Segmentation AUROC 96.0 # 1
Unsupervised Anomaly Detection KolektorSDD2 Semi-orthogonal Segmentation AUROC 98.1 # 1
Anomaly Detection MVTec AD Semi-orthogonal Segmentation AUROC 98.2 # 14


No methods listed for this paper. Add relevant methods here