mlsanityData to 7 Oct 2026

Explainable Deep One-Class Classification

arXiv 2007.01760 ↗First posted 3 Jul 2020cs.CV cs.LG stat.MLcited by 126

Not on the map. Why?

Abstract (arXiv)

Deep one-class classification variants for anomaly detection learn a mapping that concentrates nominal samples in feature space causing anomalies to be mapped away. Because this transformation is highly non-linear, finding interpretations poses a significant challenge. In this paper we present an explainable deep one-class classification method, Fully Convolutional Data Description (FCDD), where the mapped samples are themselves also an explanation heatmap. FCDD yields competitive detection performance and provides reasonable explanations on common anomaly detection benchmarks with CIFAR-10 and ImageNet. On MVTec-AD, a recent manufacturing dataset offering ground-truth anomaly maps, FCDD sets a new state of the art in the unsupervised setting. Our method can incorporate ground-truth anomaly maps during training and using even a few of these (~5) improves performance significantly. Finally, using FCDD's explanations we demonstrate the vulnerability of deep one-class classification models to spurious image features such as image watermarks.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 27; 2023: 34; 2024: 24; 2025: 14; 2026: 8.

126 papers.

Sort:

By area:

  1. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  2. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  3. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  4. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  5. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  6. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  7. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  8. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  9. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  10. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  11. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  12. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
38 more
  1. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  2. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  3. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  4. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  5. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  6. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  7. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  8. 2022A Survey on Explainable Anomaly Detectioncited by 39
  9. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  10. 2021One-Class Classification: A Surveycited by 35
  11. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  12. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  13. 2021Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localizationcited by 32
  14. 2022ADTR: Anomaly Detection Transformer with Feature Reconstructioncited by 31
  15. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  16. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  17. 2021Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentationcited by 26
  18. 2023Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learningcited by 25
  19. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  20. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 24
  21. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
  22. 2021AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learningcited by 21
  23. 2022A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Imagescited by 21
  24. 2022Data-Efficient and Interpretable Tabular Anomaly Detectioncited by 15
  25. 2023Beyond Individual Input for Deep Anomaly Detection on Tabular Datacited by 14
  26. 2023Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detectioncited by 14
  27. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detectioncited by 13
  28. 2021AnomalyHop: An SSL-based Image Anomaly Localization Methodcited by 12
  29. 2023Deep Orthogonal Hypersphere Compression for Anomaly Detectioncited by 12
  30. 2024A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teamscited by 12
  31. 2024SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detectioncited by 12
  32. 2021PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimationcited by 11
  33. 2022A Survey of Visual Sensory Anomaly Detectioncited by 11
  34. 2023ProtoFL: Unsupervised Federated Learning via Prototypical Distillationcited by 11
  35. 2023UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detectioncited by 11
  36. 2021Contrastive Predictive Coding for Anomaly Detectioncited by 10
  37. 2021Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representationscited by 10
  38. 2023Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localizationcited by 10

50 most cited of 126 All 126 (JSON)