mlsanityData to 14 Oct 2026

Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection

arXiv 2111.09099 ↗First posted 17 Nov 2021cs.CV cs.LGcited by 119

Not on the map. Why?

Abstract (arXiv)

Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abnormal test samples. Among the successful approaches for anomaly detection, a distinguished category of methods relies on predicting masked information (e.g. patches, future frames, etc.) and leveraging the reconstruction error with respect to the masked information as an abnormality score. Different from related methods, we propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. The proposed self-supervised block is generic and can easily be incorporated into various state-of-the-art anomaly detection methods. Our block starts with a convolutional layer with dilated filters, where the center area of the receptive field is masked. The resulting activation maps are passed through a channel attention module. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video, providing empirical evidence that shows considerable performance improvements on MVTec AD, Avenue, and ShanghaiTech. We release our code as open source at https://github.com/ristea/sspcab.

Key facts. Cited by 119 papers in the map (data through 14 Oct 2026). Builds on 44 of its 83 references that are in the map. First posted on arXiv 17 Nov 2021.

Builds on

44 of 83 references.

References · 44

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017Squeeze-and-Excitation Networkscited by 4,789
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  4. 2017Dynamic Routing Between Capsulescited by 689
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  6. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  7. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  9. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  10. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
32 more
  1. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  2. 2016Learning Temporal Regularity in Video Sequencescited by 254
  3. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  4. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  5. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  6. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  7. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  8. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  9. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  10. 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 90
  11. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  12. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 86
  13. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  14. 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
  15. 2020Video Cloze Procedure for Self-Supervised Spatio-Temporal Learningcited by 81
  16. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  17. 2018Context-encoding Variational Autoencoder for Unsupervised Anomaly Detectioncited by 64
  18. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  19. 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
  20. 2016Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenescited by 50
  21. 2017Unmasking the abnormal events in videocited by 48
  22. 2020Any-Shot Sequential Anomaly Detection in Surveillance Videoscited by 34
  23. 2016Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detectioncited by 32
  24. 2020Learning a distance function with a Siamese network to localize anomalies in videoscited by 31
  25. 2021Learning Not to Reconstruct Anomaliescited by 31
  26. 2018Detecting abnormal events in video using Narrowed Normality Clusterscited by 30
  27. 2018Anomaly Detection using Deep Learning based Image Completioncited by 27
  28. 2021Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detectioncited by 26
  29. 2016A Discriminative Framework for Anomaly Detection in Large Videoscited by 25
  30. 2018AVID: Adversarial Visual Irregularity Detectioncited by 19
  31. 2018STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detectioncited by 17
  32. 2021Discriminative-Generative Dual Memory Video Anomaly Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 16; 2023: 31; 2024: 33; 2025: 23; 2026: 16.

119 papers.

Sort:

By area:

  1. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  2. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  3. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  4. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  5. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  6. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  7. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68
  8. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  9. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 60
  10. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  11. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  12. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
38 more
  1. 2023CaptainCook4D: A Dataset for Understanding Errors in Procedural Activitiescited by 51
  2. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 49
  3. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detectioncited by 46
  4. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  5. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 42
  6. 2024Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Promptscited by 40
  7. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  8. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detectioncited by 36
  9. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  10. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  11. 2024Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generationcited by 32
  12. 2024Masked Image Modeling: A Surveycited by 29
  13. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  14. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  15. 2022Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detectioncited by 26
  16. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 26
  17. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  18. 2023Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learningcited by 25
  19. 2023MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detectioncited by 25
  20. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  21. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
  22. 2024MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detectioncited by 22
  23. 2022A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Imagescited by 21
  24. 2022EVAL: Explainable Video Anomaly Localizationcited by 19
  25. 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
  26. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  27. 2023Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detectioncited by 16
  28. 2024Self-supervised Feature Adaptation for 3D Industrial Anomaly Detectioncited by 16
  29. 2024Continuous Memory Representation for Anomaly Detectioncited by 16
  30. 2024CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generationcited by 16
  31. 2023Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attentioncited by 15
  32. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  33. 2023Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detectioncited by 14
  34. 2024Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Imagescited by 13
  35. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 13
  36. 2023Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Spacecited by 12
  37. 2025Modeling Multiple Normal Action Representations for Error Detection in Procedural Taskscited by 12
  38. 2022Anomaly Detection in Aerial Videos with Transformerscited by 11

50 most cited of 119 All 119 (JSON)