mlsanityData to 14 Oct 2026

SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation

arXiv 2412.20870 ↗First posted 30 Dec 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Although mainstream unsupervised anomaly detection (AD) (including image-level classification and pixel-level segmentation)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 is the first to consider fully unsupervised industrial anomaly detection (i.e., unsupervised AD with noisy data). To solve this problem, we proposed memory-based unsupervised AD methods, SoftPatch and SoftPatch+, which efficiently denoise 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, and SoftPatch+ has more robust performance which is articularly useful in real-world industrial inspection scenarios with high levels of noise (from 10% to 40%). Comprehensive experiments conducted in diverse noise scenarios demonstrate that both SoftPatch and SoftPatch+ outperform the state-of-the-art AD methods on the MVTecAD, ViSA, and BTAD benchmarks. Furthermore, the performance of SoftPatch and SoftPatch+ is comparable to that of the noise-free methods in conventional unsupervised AD setting. The code of the proposed methods can be found at https://github.com/TencentYoutuResearch/AnomalyDetection-SoftPatch.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

31 of 40 references.

References · 31

  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. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  7. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  8. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  9. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
19 more
  1. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  2. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  3. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  4. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  5. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  6. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  7. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  8. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  9. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 90
  10. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  11. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  12. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  13. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  14. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  15. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  16. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  17. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  18. 2021Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localizationcited by 32
  19. 2023SaliencyCut: Augmenting Plausible Anomalies for Anomaly Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  2. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparisoncited by 5
  3. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 4
  4. 2025An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contaminationcited by 3
  5. 2025Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Eracited by 2
  6. 2026AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutationcited by 0
  7. 2026What Memory Composition Does Not Tell Us About Anomaly Detectioncited by 0