Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation
This work addresses a scalability problem for researchers and practitioners using deep learning in anomaly detection, offering an incremental improvement over existing methods.
The paper tackles the computational inefficiency of using multi-scale features from pre-trained CNNs for unsupervised anomaly segmentation by proposing semi-orthogonal embedding, which reduces the cost of covariance tensor inversion and achieves state-of-the-art results on multiple datasets with significant margins.
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.