mlsanityData to 14 Oct 2026

Anomaly Detection Requires Better Representations

arXiv 2210.10773 ↗First posted 19 Oct 2022cs.LG cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation learning have directly driven improvements in anomaly detection. In this position paper, we first explain how self-supervised representations can be easily used to achieve state-of-the-art performance in commonly reported anomaly detection benchmarks. We then argue that tackling the next generation of anomaly detection tasks requires new technical and conceptual improvements in representation learning.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

23 of 39 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  6. 2016Colorful Image Colorizationcited by 1,114
  7. 2020Concept Bottleneck Modelscited by 1,032
  8. 2021ImageNet-21K Pretraining for the Massescited by 613
  9. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  10. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  11. 2015Deep multi-scale video prediction beyond mean square errorcited by 300
  12. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
11 more
  1. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  2. 2016Learning Representations for Automatic Colorizationcited by 251
  3. 2020Classification-Based Anomaly Detection for General Datacited by 211
  4. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  5. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  6. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  7. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  8. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  9. 2018Learning Deep Features for One-Class Classificationcited by 76
  10. 2022A Contrastive Objective for Learning Disentangled Representationscited by 14
  11. 2022Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factorscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 6; 2025: 1; 2026: 1.

15 papers.

Sort:

By area:

  1. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  2. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  3. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  4. 2023Set Features for Fine-grained Anomaly Detectioncited by 13
  5. 2023No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detectioncited by 7
  6. 2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
  7. 2024Rethinking cluster-conditioned diffusion models for label-free image synthesiscited by 5
  8. 2024Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detectioncited by 5
  9. 2023SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasetscited by 4
  10. 2023Understanding the limitations of self-supervised learning for tabular anomaly detectioncited by 3
  11. 2023Set Features for Anomaly Detectioncited by 3
  12. 2024Critical Review for One-class Classification: recent advances and the reality behind themcited by 2
3 more
  1. 2023Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challengecited by 1
  2. 2024When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detectioncited by 1
  3. 2026Hidden Activations are not Enough I: Knowledge Matrices as Higher Representationscited by 0