mlsanityData to 7 Oct 2026

Student-Teacher Feature Pyramid Matching for Anomaly Detection

arXiv 2103.04257 ↗First posted 7 Mar 2021cs.CVcited by 145

Not on the map. Why?

Abstract (arXiv)

Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies. This paper proposes a simple yet powerful approach to this issue, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency. Given a strong model pre-trained on image classification as the teacher, we distill the knowledge into a single student network with the identical architecture to learn the distribution of anomaly-free images and this one-step transfer preserves the crucial clues as much as possible. Moreover, we integrate the multi-scale feature matching strategy into the framework, and this hierarchical feature matching enables the student network to receive a mixture of multi-level knowledge from the feature pyramid under better supervision, thus allowing to detect anomalies of various sizes. The difference between feature pyramids generated by the two networks serves as a scoring function indicating the probability of anomaly occurring. Due to such operations, our approach achieves accurate and fast pixel-level anomaly detection. Very competitive results are delivered on the MVTec anomaly detection dataset, superior to the state of the art ones.

Key facts. Cited by 145 papers in the map (data through 7 Oct 2026). Builds on 25 of its 48 references that are in the map. First posted on arXiv 7 Mar 2021.

Builds on

25 of 48 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2016Wide Residual Networkscited by 3,057
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  6. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  7. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  8. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  9. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  10. 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 312
  11. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  12. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
13 more
  1. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  2. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  3. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  4. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  5. 2018Adversarially Learned Anomaly Detectioncited by 115
  6. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  7. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  8. 2016Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenescited by 50
  9. 2018q-Space Novelty Detection with Variational Autoencoderscited by 22
  10. 2018Metric Learning for Novelty and Anomaly Detectioncited by 21
  11. 2016Identifying and Categorizing Anomalies in Retinal Imaging Datacited by 18
  12. 2018Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representationscited by 17
  13. 2018Informed Democracy: Voting-based Novelty Detection for Action Recognitioncited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 30; 2024: 47; 2025: 29; 2026: 28.

145 papers.

Sort:

By area:

  1. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  2. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  3. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  4. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  5. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  6. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  7. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  8. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 97
  9. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  10. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  11. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  12. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
38 more
  1. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 72
  2. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  3. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  4. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 62
  5. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 59
  6. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 56
  7. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  8. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  9. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  10. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 41
  11. 2023Anomaly Detection under Distribution Shiftcited by 35
  12. 2024Unsupervised Continual Anomaly Detection with Contrastively-learned Promptcited by 31
  13. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 28
  14. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  15. 2024SplatPose & Detect: Pose-Agnostic 3D Anomaly Detectioncited by 25
  16. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  17. 2023Unsupervised Pathology Detection: A Deep Dive Into the State of the Artcited by 24
  18. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  19. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  20. 2023Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detectioncited by 21
  21. 2022Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimationcited by 20
  22. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  23. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  24. 2024Self-supervised Feature Adaptation for 3D Industrial Anomaly Detectioncited by 16
  25. 2024Continuous Memory Representation for Anomaly Detectioncited by 16
  26. 2024PaSTe: Improving the Efficiency of Visual Anomaly Detection at the Edgecited by 16
  27. 2024Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learningcited by 13
  28. 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samplescited by 12
  29. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 12
  30. 2022Learning image representations for anomaly detection: application to discovery of histological alterations in drug developmentcited by 11
  31. 2023SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classificationcited by 10
  32. 2023A Discrepancy Aware Framework for Robust Anomaly Detectioncited by 9
  33. 2023What makes a good data augmentation for few-shot unsupervised image anomaly detection?cited by 8
  34. 2023Invariant Anomaly Detection under Distribution Shifts: A Causal Perspectivecited by 8
  35. 2024Unlocking the Potential of Reverse Distillation for Anomaly Detectioncited by 8
  36. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  37. 2022Unsupervised Visual Defect Detection with Score-Based Generative Modelcited by 7
  38. 2023Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videoscited by 7

50 most cited of 145 All 145 (JSON)