mlsanityData to 14 Oct 2026

Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization

arXiv 2302.08769 ↗First posted 17 Feb 2023cs.CV cs.AIcited by 57

Not on the map. Why?

Abstract (arXiv)

Most unsupervised image anomaly localization methods suffer from overgeneralization because of the high generalization abilities of convolutional neural networks, leading to unreliable predictions. To mitigate the overgeneralization, this study proposes to collaboratively optimize normal and abnormal feature distributions with the assistance of synthetic anomalies, namely collaborative discrepancy optimization (CDO). CDO introduces a margin optimization module and an overlap optimization module to optimize the two key factors determining the localization performance, i.e., the margin and the overlap between the discrepancy distributions (DDs) of normal and abnormal samples. With CDO, a large margin and a small overlap between normal and abnormal DDs are obtained, and the prediction reliability is boosted. Experiments on MVTec2D and MVTec3D show that CDO effectively mitigates the overgeneralization and achieves great anomaly localization performance with real-time computation efficiency. A real-world automotive plastic parts inspection application further demonstrates the capability of the proposed CDO. Code is available on https://github.com/caoyunkang/CDO.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

18 of 35 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Wide Residual Networkscited by 3,070
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  4. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  5. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  6. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  7. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  8. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  9. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  10. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  11. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  12. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
6 more
  1. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  2. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  3. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  4. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 146
  5. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  6. 2020DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentationcited by 54

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 22; 2025: 17; 2026: 10.

57 papers.

Sort:

By area:

  1. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  2. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  3. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  4. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  5. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  6. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  7. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  8. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  9. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  10. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  11. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  12. 2024Unseen Visual Anomaly Generationcited by 23
38 more
  1. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
  2. 2024Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoningcited by 20
  3. 2024LogiCode: an LLM-Driven Framework for Logical Anomaly Detectioncited by 19
  4. 2024Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detectioncited by 19
  5. 2024Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detectioncited by 17
  6. 2024Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmarkcited by 16
  7. 2024Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Frameworkcited by 15
  8. 2024VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modelingcited by 9
  9. 2024RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detectioncited by 8
  10. 2024Towards Zero-shot 3D Anomaly Localizationcited by 8
  11. 2024Dual-path Frequency Discriminators for Few-shot Anomaly Detectioncited by 7
  12. 2025A Survey on Industrial Anomaly Synthesiscited by 7
  13. 2025Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detectioncited by 7
  14. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  15. 2023Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformerscited by 6
  16. 2024Small Object Few-shot Segmentation for Vision-based Industrial Inspectioncited by 5
  17. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  18. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  19. 2024Global-Regularized Neighborhood Regression for Efficient Zero-Shot Texture Anomaly Detectioncited by 4
  20. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 4
  21. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  22. 20232nd Place Winning Solution for the CVPR2023 Visual Anomaly and Novelty Detection Challenge: Multimodal Prompting for Data-centric Anomaly Detectioncited by 2
  23. 2024Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detectioncited by 2
  24. 2025PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awarenesscited by 2
  25. 2025ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defectscited by 2
  26. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  27. 2025Prototypical Learning Guided Context-Aware Segmentation Network for Few-Shot Anomaly Detectioncited by 2
  28. 2026VTFusion: A Vision-Text Multimodal Fusion Network for Few-Shot Anomaly Detectioncited by 2
  29. 2023Dual-Branch Reconstruction Network for Industrial Anomaly Detection with RGB-D Datacited by 1
  30. 2025HDM: Hybrid Diffusion Model for Unified Image Anomaly Detectioncited by 1
  31. 2025Zero-Shot Anomaly Detection with Dual-Branch Prompt Selectioncited by 1
  32. 2025Anomaly Detection by Effectively Leveraging Synthetic Imagescited by 1
  33. 2026Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial Applicationscited by 1
  34. 2026URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detectioncited by 1
  35. 2024Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense Predictioncited by 0
  36. 2024Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localizationcited by 0
  37. 2025Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Modelcited by 0
  38. 2025Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localizationcited by 0

50 most cited of 57 All 57 (JSON)