mlsanityData to 7 Oct 2026

Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation

arXiv 2105.14737 ↗First posted 31 May 2021cs.CV cs.AI cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

20 of 33 references.

References · 20

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  6. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  7. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  8. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  9. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  10. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  11. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  12. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
8 more
  1. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  2. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  3. 2020Explainable Deep One-Class Classificationcited by 126
  4. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  5. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  6. 2017The Unreasonable Effectiveness of Structured Random Orthogonal Embeddingscited by 43
  7. 2017OL'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learningcited by 37
  8. 2021One-Class Classification: A Surveycited by 35

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 9; 2023: 10; 2024: 5; 2025: 1.

26 papers.

Sort:

By area:

  1. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  2. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  3. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  4. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  5. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  6. 2022Mutual Information Divergence: A Unified Metric for Multimodal Generative Modelscited by 35
  7. 2023Exploring Diffusion Models for Unsupervised Video Anomaly Detectioncited by 23
  8. 2022A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Imagescited by 21
  9. 2023Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representationscited by 18
  10. 2022U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Thresholdcited by 16
  11. 2023LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detectioncited by 13
  12. 2023A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detectioncited by 13
14 more
  1. 2023What makes a good data augmentation for few-shot unsupervised image anomaly detection?cited by 8
  2. 2024Few-Shot Anomaly Detection via Category-Agnostic Registration Learningcited by 6
  3. 2022ADPS: Asymmetric Distillation Post-Segmentation for Image Anomaly Detectioncited by 5
  4. 2021Efficient Non-Compression Auto-Encoder for Driving Noise-based Road Surface Anomaly Detectioncited by 3
  5. 2024IPAD: Industrial Process Anomaly Detection Datasetcited by 3
  6. 2024ONER: Online Experience Replay for Incremental Anomaly Detectioncited by 3
  7. 2023Weakly supervised marine animal detection from remote sensing images using vector-quantized variational autoencodercited by 2
  8. 2024A Recover-then-Discriminate Framework for Robust Anomaly Detectioncited by 2
  9. 2023Dual-Branch Reconstruction Network for Industrial Anomaly Detection with RGB-D Datacited by 1
  10. 2024TeG: Temporal-Granularity Method for Anomaly Detection with Attention in Smart City Surveillancecited by 1
  11. 2022[Reproducibility Report] Explainable Deep One-Class Classificationcited by 0
  12. 2022Anomaly segmentation model for defects detection in electroluminescence images of heterojunction solar cellscited by 0
  13. 2023Gaussian Image Anomaly Detection with Greedy Eigencomponent Selectioncited by 0
  14. 2025RobustA: Robust Anomaly Detection in Multimodal Datacited by 0