mlsanityData to 7 Oct 2026

Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection

arXiv 2107.13118 ↗First posted 28 Jul 2021cs.CVcited by 83

Not on the map. Why?

Abstract (arXiv)

Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruction for abnormal samples. Since the generalizability of deep neural networks is difficult to control, existing models such as autoencoder do not work well. In this work, we interpret the reconstruction of an image as a divide-and-assemble procedure. Surprisingly, by varying the granularity of division on feature maps, we are able to modulate the reconstruction capability of the model for both normal and abnormal samples. That is, finer granularity leads to better reconstruction, while coarser granularity leads to poorer reconstruction. With proper granularity, the gap between the reconstruction error of normal and abnormal samples can be maximized. The divide-and-assemble framework is implemented by embedding a novel multi-scale block-wise memory module into an autoencoder network. Besides, we introduce adversarial learning and explore the semantic latent representation of the discriminator, which improves the detection of subtle anomaly. We achieve state-of-the-art performance on the challenging MVTec AD dataset. Remarkably, we improve the vanilla autoencoder model by 10.1% in terms of the AUROC score.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). Builds on 32 of its 57 references that are in the map. First posted on arXiv 28 Jul 2021.

Builds on

32 of 57 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  7. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  8. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  9. 2014Memory Networkscited by 354
  10. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  11. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  12. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
20 more
  1. 2016Learning Temporal Regularity in Video Sequencescited by 254
  2. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  3. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  4. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  5. 2019Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answeringcited by 146
  6. 2018Efficient GAN-Based Anomaly Detectioncited by 122
  7. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  8. 2020MAST: A Memory-Augmented Self-supervised Trackercited by 109
  9. 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
  10. 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
  11. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  12. 2020MANTRA: Memory Augmented Networks for Multiple Trajectory Predictioncited by 69
  13. 2018Learning Dynamic Memory Networks for Object Trackingcited by 58
  14. 2020Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noisecited by 39
  15. 2016Scaling Memory-Augmented Neural Networks with Sparse Reads and Writescited by 28
  16. 2020Anomaly localization by modeling perceptual featurescited by 21
  17. 2019Attribute Restoration Framework for Anomaly Detectioncited by 16
  18. 2020Memory Augmented Generative Adversarial Networks for Anomaly Detectioncited by 12
  19. 2019adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detectioncited by 11
  20. 2019Memory-Augmented Temporal Dynamic Learning for Action Recognitioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 15; 2023: 27; 2024: 19; 2025: 8; 2026: 13.

83 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. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  4. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  5. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  6. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  7. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  8. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 81
  9. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  10. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  11. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  12. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 59
38 more
  1. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  2. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  3. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  4. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detectioncited by 46
  5. 2023Diversity-Measurable Anomaly Detectioncited by 41
  6. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 41
  7. 2024Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Promptscited by 40
  8. 2023Anomaly Detection under Distribution Shiftcited by 35
  9. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  10. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 28
  11. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  12. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
  13. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  14. 2022Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimationcited by 20
  15. 2022Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detectioncited by 18
  16. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  17. 2022FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detectioncited by 16
  18. 2024Self-supervised Feature Adaptation for 3D Industrial Anomaly Detectioncited by 16
  19. 2024Continuous Memory Representation for Anomaly Detectioncited by 16
  20. 2024Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detectioncited by 16
  21. 2023Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detectioncited by 14
  22. 2023FDCT: Fast Depth Completion for Transparent Objectscited by 12
  23. 2024AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localizationcited by 12
  24. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 12
  25. 2022A Survey of Visual Sensory Anomaly Detectioncited by 11
  26. 2024Fair Anomaly Detection For Imbalanced Groupscited by 10
  27. 2022Normal Reference Attention and Defective Feature Perception Network for Surface Defect Detectioncited by 9
  28. 2023Real Face Foundation Representation Learning for Generalized Deepfake Detectioncited by 8
  29. 2022Unsupervised Visual Defect Detection with Score-Based Generative Modelcited by 7
  30. 2023A Prototype-Based Neural Network for Image Anomaly Detection and Localizationcited by 7
  31. 2024SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentationcited by 7
  32. 2023Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformerscited by 6
  33. 2024AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Modelcited by 6
  34. 2021Data Invariants to Understand Unsupervised Out-of-Distribution Detectioncited by 5
  35. 2022ADPS: Asymmetric Distillation Post-Segmentation for Image Anomaly Detectioncited by 5
  36. 2023Multi-level Memory-augmented Appearance-Motion Correspondence Framework for Video Anomaly Detectioncited by 5
  37. 2023Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial Visioncited by 5
  38. 2023Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representationscited by 5

50 most cited of 83 All 83 (JSON)