mlsanityData to 14 Oct 2026

SoftPatch: Unsupervised Anomaly Detection with Noisy Data

arXiv 2403.14233 ↗First posted 21 Mar 2024cs.CV cs.AI cs.LGcited by 55

Not on the map. Why?

Abstract (arXiv)

Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experimental setting of clean training data. Training with noisy data is an inevitable problem in real-world anomaly detection but is seldom discussed. This paper considers label-level noise in image sensory anomaly detection for the first time. To solve this problem, we proposed a memory-based unsupervised AD method, SoftPatch, which efficiently denoises the data at the patch level. Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction. The scores are then stored in the memory bank to soften the anomaly detection boundary. Compared with existing methods, SoftPatch maintains a strong modeling ability of normal data and alleviates the overconfidence problem in coreset. Comprehensive experiments in various noise scenes demonstrate that SoftPatch outperforms the state-of-the-art AD methods on the MVTecAD and BTAD benchmarks and is comparable to those methods under the setting without noise.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

36 of 46 references.

References · 36

  1. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  4. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  8. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  9. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  10. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  11. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  12. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
24 more
  1. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  2. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  3. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  4. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  5. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  6. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  7. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  8. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  9. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  10. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 90
  11. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  12. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  13. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  14. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  15. 2022MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiescited by 68
  16. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68
  17. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  18. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  19. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  20. 2020Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Imagescited by 52
  21. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  22. 2021Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localizationcited by 32
  23. 2021Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detectioncited by 20
  24. 2022Data refinement for fully unsupervised visual inspection using pre-trained networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 24; 2026: 15.

55 papers.

Sort:

By area:

  1. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  2. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detectioncited by 47
  3. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 26
  4. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  5. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  6. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 13
  7. 2024Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspectivecited by 12
  8. 2024Fair Anomaly Detection For Imbalanced Groupscited by 10
  9. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  10. 2024Learning Multi-view Anomaly Detection with Efficient Adaptive Selectioncited by 9
  11. 2024FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Datacited by 8
  12. 2024SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentationcited by 7
38 more
  1. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  2. 2024TimeInf: Time Series Data Contribution via Influence Functionscited by 6
  3. 2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
  4. 2024Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detectioncited by 5
  5. 2025Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shiftcited by 5
  6. 2025TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detectioncited by 5
  7. 2025Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detectioncited by 5
  8. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparisoncited by 5
  9. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  10. 2025An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contaminationcited by 3
  11. 2024Absolute-Unified Multi-Class Anomaly Detection via Class-Agnostic Distribution Alignmentcited by 2
  12. 2024CKNN: Cleansed k-Nearest Neighbor for Unsupervised Video Anomaly Detectioncited by 2
  13. 2024Cluster-Wide Task Slowdown Detection in Cloud Systemcited by 2
  14. 2025KairosAD: A SAM-Based Model for Industrial Anomaly Detection on Embedded Devicescited by 2
  15. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  16. 2025Unsupervised Defect Detection for Surgical Instrumentscited by 2
  17. 2025Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Eracited by 2
  18. 2025ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categoriescited by 2
  19. 2024Beyond the Known: Adversarial Autoencoders in Novelty Detectioncited by 1
  20. 2025Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detectioncited by 1
  21. 2025SEM-CLIP: Precise Few-Shot Learning for Nanoscale Defect Detection in Scanning Electron Microscope Imagecited by 1
  22. 2025BenchReAD: A systematic benchmark for retinal anomaly detectioncited by 1
  23. 2025Leveraging Learning Bias for Noisy Anomaly Detectioncited by 1
  24. 2025ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretrainingcited by 1
  25. 2026Multimodal Industrial Anomaly Detection via Geometric Priorcited by 1
  26. 2026Memory-Distilled Selection for Noise-Robust Anomaly Detectioncited by 1
  27. 2026ProCon: Projection-Consistency Memory for Training-Free Anomaly Detectioncited by 1
  28. 2025Retrospective Memory for Camouflaged Object Detectioncited by 0
  29. 2025Anomalous Samples for Few-Shot Anomaly Detectioncited by 0
  30. 2025Self-Navigated Residual Mamba for Universal Industrial Anomaly Detectioncited by 0
  31. 2025Isolating to Harness: Cross-Division Distillation for Fully Unsupervised Anomaly Detectioncited by 0
  32. 2025Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learningcited by 0
  33. 2025Explainable Deep Convolutional Multi-Type Anomaly Detectioncited by 0
  34. 2026ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modellingcited by 0
  35. 2026CINDI: Conditional Imputation and Noisy Data Integrity with Flows in Power Grid Datacited by 0
  36. 2026AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutationcited by 0
  37. 2026Evidential Reasoning Advances Interpretable Real-World Disease Screeningcited by 0
  38. 2026TimeLAVA: Learning-Agnostic Valuation for Time Series Datacited by 0

50 most cited of 55 All 55 (JSON)