mlsanityData to 7 Oct 2026

Learning Multi-view Anomaly Detection with Efficient Adaptive Selection

arXiv 2407.11935 ↗First posted 16 Jul 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

This study explores the recently proposed and challenging multi-view Anomaly Detection (AD) task. Single-view tasks will encounter blind spots from other perspectives, resulting in inaccuracies in sample-level prediction. Therefore, we introduce the Multi-View Anomaly Detection (MVAD) approach, which learns and integrates features from multi-views. Specifically, we propose a Multi-View Adaptive Selection (MVAS) algorithm for feature learning and fusion across multiple views. The feature maps are divided into neighbourhood attention windows to calculate a semantic correlation matrix between single-view windows and all other views, which is an attention mechanism conducted for each single-view window and the top-k most correlated multi-view windows. Adjusting the window sizes and top-k can minimise the complexity to O((hw)^4/3). Extensive experiments on the Real-IAD dataset under the multi-class setting validate the effectiveness of our approach, achieving state-of-the-art performance with an average improvement of +2.5 across 10 metrics at the sample/image/pixel levels, using only 18M parameters and requiring fewer FLOPs and training time. The codes are available at https://github.com/lewandofskee/MVAD.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 45 of its 62 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

45 of 62 references.

References · 45

  1. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  2. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  4. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  6. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  7. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  8. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  9. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  11. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  12. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
33 more
  1. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  2. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  3. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  4. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  5. 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 204
  6. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  7. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  8. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  9. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  10. 2022Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detectioncited by 145
  11. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  12. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  13. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  14. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  15. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  16. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 79
  17. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  18. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  19. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  20. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  21. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  22. 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 50
  23. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  24. 2021CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detectioncited by 47
  25. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  26. 2022Self-Supervised Masking for Unsupervised Anomaly Detection and Localizationcited by 43
  27. 2023AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perceptioncited by 39
  28. 2016Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNscited by 29
  29. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  30. 2021Prior-Guided Multi-View 3D Head Reconstructioncited by 14
  31. 2021FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstructioncited by 11
  32. 2024A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detectioncited by 7
  33. 2023Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modelingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusioncited by 3
  2. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 3
  3. 2025Learning Multi-view Multi-class Anomaly Detectioncited by 1
  4. 2026IMMoE: Incomplete Multi-View Anomaly Detection via Mixture of View Experts Fusioncited by 1
  5. 2026SGANet: Semantic and Geometric Alignment for Multimodal Multi-view Anomaly Detectioncited by 0
  6. 2026MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detectioncited by 0
  7. 2026MATCH: Flow Matching for Multi-View Anomaly Detectioncited by 0
  8. 2026See More, Detect Less? Taming Information Leakage in Multi-View Anomaly Detectioncited by 0
  9. 2026GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignmentcited by 0