mlsanityData to 7 Oct 2026

Contextual Affinity Distillation for Image Anomaly Detection

arXiv 2307.03101 ↗First posted 6 Jul 2023cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Previous works on unsupervised industrial anomaly detection mainly focus on local structural anomalies such as cracks and color contamination. While achieving significantly high detection performance on this kind of anomaly, they are faced with logical anomalies that violate the long-range dependencies such as a normal object placed in the wrong position. In this paper, based on previous knowledge distillation works, we propose to use two students (local and global) to better mimic the teacher's behavior. The local student, which is used in previous studies mainly focuses on structural anomaly detection while the global student pays attention to logical anomalies. To further encourage the global student's learning to capture long-range dependencies, we design the global context condensing block (GCCB) and propose a contextual affinity loss for the student training and anomaly scoring. Experimental results show the proposed method doesn't need cumbersome training techniques and achieves a new state-of-the-art performance on the MVTec LOCO AD dataset.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 6 Jul 2023.

Builds on

29 of 41 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2016Wide Residual Networkscited by 3,057
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  11. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  12. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
17 more
  1. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  2. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  3. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  4. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  5. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  6. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  7. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  8. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  9. 2019Structured Knowledge Distillation for Dense Predictioncited by 277
  10. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  11. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  12. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  13. 2020Channel-wise Knowledge Distillation for Dense Predictioncited by 161
  14. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  15. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 89
  16. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
  17. 2020G2D: Generate to Detect Anomalycited by 42

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 8; 2026: 1.

18 papers.

Sort:

  1. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  2. 2023Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Leadcited by 40
  3. 2024SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detectioncited by 14
  4. 2024CSAD: Unsupervised Component Segmentation for Logical Anomaly Detectioncited by 11
  5. 2024Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detectioncited by 10
  6. 2024Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detectioncited by 5
  7. 2025"Stones from Other Hills can Polish Jade": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injectioncited by 3
  8. 2025SALAD -- Semantics-Aware Logical Anomaly Detectioncited by 3
  9. 2025An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contaminationcited by 3
  10. 2024Detecting Abnormal Operations in Concentrated Solar Power Plants from Irregular Sequences of Thermal Imagescited by 2
  11. 2026UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detectioncited by 1
  12. 2024Separating Novel Features for Logical Anomaly Detection: A Straightforward yet Effective Approachcited by 0
6 more
  1. 2024Tuned Reverse Distillation: Enhancing Multimodal Industrial Anomaly Detection with Crossmodal Tunerscited by 0
  2. 2025Risk-Based Thresholding for Reliable Anomaly Detection in Concentrated Solar Power Plantscited by 0
  3. 2025Learning local and global prototypes with optimal transport for unsupervised anomaly detection and localizationcited by 0
  4. 2025TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bankcited by 0
  5. 2025Generalist Multi-Class Anomaly Detection via Distillation to Two Heterogeneous Student Networkscited by 0
  6. 2025Physic-HM: Restoring Physical Generative Logic in Multimodal Anomaly Detection via Hierarchical Modulationcited by 0