mlsanityData to 14 Oct 2026

Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection

arXiv 2308.02983 ↗First posted 6 Aug 2023cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Humans recognize anomalies through two aspects: larger patch-wise representation discrepancies and weaker patch-to-normal-patch correlations. However, the previous AD methods didn't sufficiently combine the two complementary aspects to design AD models. To this end, we find that Transformer can ideally satisfy the two aspects as its great power in the unified modeling of patch-wise representations and patch-to-patch correlations. In this paper, we propose a novel AD framework: FOcus-the-Discrepancy (FOD), which can simultaneously spot the patch-wise, intra- and inter-discrepancies of anomalies. The major characteristic of our method is that we renovate the self-attention maps in transformers to Intra-Inter-Correlation (I2Correlation). The I2Correlation contains a two-branch structure to first explicitly establish intra- and inter-image correlations, and then fuses the features of two-branch to spotlight the abnormal patterns. To learn the intra- and inter-correlations adaptively, we propose the RBF-kernel-based target-correlations as learning targets for self-supervised learning. Besides, we introduce an entropy constraint strategy to solve the mode collapse issue in optimization and further amplify the normal-abnormal distinguishability. Extensive experiments on three unsupervised real-world AD benchmarks show the superior performance of our approach. Code will be available at https://github.com/xcyao00/FOD.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 52 of its 66 references that are in the map. First posted on arXiv 6 Aug 2023.

Builds on

52 of 66 references.

References · 52

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2017Neural Discrete Representation Learningcited by 4,712
  9. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  12. 2021Grounded Language-Image Pre-trainingcited by 1,156
38 more
  1. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  2. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  3. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  4. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  5. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  6. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  7. 2019GhostNet: More Features from Cheap Operationscited by 410
  8. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  9. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  10. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  13. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  14. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  15. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  16. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  17. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  18. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  19. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  20. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  21. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  22. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  23. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  24. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  25. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  26. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  27. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  28. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  29. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  30. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  31. 2020Deep Nearest Neighbor Anomaly Detectioncited by 104
  32. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  33. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  34. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 90
  35. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  36. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  37. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  38. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 10; 2025: 11; 2026: 8.

32 papers.

Sort:

By area:

  1. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  2. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  3. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  4. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28
  5. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 27
  6. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  7. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 25
  8. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  9. 2024Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detectioncited by 19
  10. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  11. 2024CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generationcited by 16
  12. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 13
20 more
  1. 2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformercited by 11
  2. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  3. 2024A SAM-guided Two-stream Lightweight Model for Anomaly Detectioncited by 7
  4. 2024Promptable Anomaly Segmentation with SAM Through Self-Perception Tuningcited by 7
  5. 2025Towards Accurate Unified Anomaly Segmentationcited by 7
  6. 2025SALAD -- Semantics-Aware Logical Anomaly Detectioncited by 4
  7. 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detectioncited by 4
  8. 2024Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detectioncited by 2
  9. 2025KairosAD: A SAM-Based Model for Industrial Anomaly Detection on Embedded Devicescited by 2
  10. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  11. 2023Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detectioncited by 1
  12. 2026URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detectioncited by 1
  13. 2026MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Modelscited by 1
  14. 2025Bi-Grid Reconstruction for Image Anomaly Detectioncited by 0
  15. 2025Domain Adaptation of Attention Heads for Zero-shot Anomaly Detectioncited by 0
  16. 2025Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environmentscited by 0
  17. 2026A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detectioncited by 0
  18. 2026InCTRLv2: Generalist Residual Models for Few-Shot Anomaly Detection and Segmentationcited by 0
  19. 2026Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detectioncited by 0
  20. 2026Value-order Decomposition for Generalist Anomaly Detectioncited by 0