mlsanityData to 7 Oct 2026

Set Features for Fine-grained Anomaly Detection

arXiv 2302.12245 ↗First posted 23 Feb 2023cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Fine-grained anomaly detection has recently been dominated by segmentation based approaches. These approaches first classify each element of the sample (e.g., image patch) as normal or anomalous and then classify the entire sample as anomalous if it contains anomalous elements. However, such approaches do not extend to scenarios where the anomalies are expressed by an unusual combination of normal elements. In this paper, we overcome this limitation by proposing set features that model each sample by the distribution its elements. We compute the anomaly score of each sample using a simple density estimation method. Our simple-to-implement approach outperforms the state-of-the-art in image-level logical anomaly detection (+3.4%) and sequence-level time-series anomaly detection (+2.4%).

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 23 Feb 2023.

Builds on

31 of 56 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Billion-scale similarity search with GPUscited by 2,477
  3. 2017Deep Setscited by 1,394
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  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. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  8. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  9. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  10. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
19 more
  1. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  2. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  3. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  4. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  5. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  6. 2016Learning Representations for Automatic Colorizationcited by 251
  7. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
  8. 2020Classification-Based Anomaly Detection for General Datacited by 210
  9. 2020A review on outlier/anomaly detection in time series datacited by 187
  10. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 186
  11. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  12. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  13. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
  14. 2018Learning Deep Features for One-Class Classificationcited by 76
  15. 2015The Radon cumulative distribution transform and its application to image classificationcited by 28
  16. 2017Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Networkcited by 28
  17. 2021Transformaly -- Two (Feature Spaces) Are Better Than Onecited by 25
  18. 2022Anomaly Detection Requires Better Representationscited by 14
  19. 2022No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 3; 2025: 2; 2026: 1.

13 papers.

Sort:

By area:

  1. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Modelscited by 24
  2. 2023Component-aware anomaly detection framework for adjustable and logical industrial visual inspectioncited by 22
  3. 2023Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detectioncited by 21
  4. 2023Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detectioncited by 19
  5. 2023Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detectioncited by 14
  6. 2023REB: Reducing Biases in Representation for Industrial Anomaly Detectioncited by 9
  7. 2024PUAD: Frustratingly Simple Method for Robust Anomaly Detectioncited by 7
  8. 2024LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localizationcited by 6
  9. 2023Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flowcited by 3
  10. 2024MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detectioncited by 2
  11. 2023Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challengecited by 1
  12. 2026HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detectioncited by 1
1 more
  1. 2025Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly Detectioncited by 0