mlsanityData to 14 Oct 2026

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection

arXiv 2404.06564 ↗First posted 9 Apr 2024cs.CVcited by 113

On the map: State-space sequence models (S4, Mamba) → Time series forecasting with SSMs

Abstract (arXiv)

Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity. Mamba-based models, with their superior long-range modeling and linear efficiency, have garnered substantial attention. This study pioneers the application of Mamba to multi-class unsupervised anomaly detection, presenting MambaAD, which consists of a pre-trained encoder and a Mamba decoder featuring (Locality-Enhanced State Space) LSS modules at multi-scales. The proposed LSS module, integrating parallel cascaded (Hybrid State Space) HSS blocks and multi-kernel convolutions operations, effectively captures both long-range and local information. The HSS block, utilizing (Hybrid Scanning) HS encoders, encodes feature maps into five scanning methods and eight directions, thereby strengthening global connections through the (State Space Model) SSM. The use of Hilbert scanning and eight directions significantly improves feature sequence modeling. Comprehensive experiments on six diverse anomaly detection datasets and seven metrics demonstrate state-of-the-art performance, substantiating the method's effectiveness. The code and models are available at https://lewandofskee.github.io/projects/MambaAD.

Key facts. Cited by 113 papers in the map (data through 14 Oct 2026). Placed in Time series forecasting with SSMs, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 45 of its 60 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

45 of 60 references.

References · 45

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  3. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  4. 2024VMamba: Visual State Space Modelcited by 969
  5. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  6. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  8. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  9. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  10. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  12. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 499
33 more
  1. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  2. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  3. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  4. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  5. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 287
  6. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  7. 2022Long Range Language Modeling via Gated State Spacescited by 265
  8. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  9. 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 236
  10. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  11. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 179
  12. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  13. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  14. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  15. 2024Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentationcited by 133
  16. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  17. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  18. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  19. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  20. 2024Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inferencecited by 97
  21. 2024VL-Mamba: Exploring State Space Models for Multimodal Learningcited by 93
  22. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  23. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  24. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
  25. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  26. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  27. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  28. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  29. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  30. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  31. 2024H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentationcited by 35
  32. 2022EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithmcited by 27
  33. 2021Analogous to Evolutionary Algorithm: Designing a Unified Sequence Modelcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 28; 2025: 47; 2026: 38.

113 papers.

Sort:

By area:

  1. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  2. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  3. 2024Vision Mamba: A Comprehensive Survey and Taxonomycited by 54
  4. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  5. 2024LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexitycited by 43
  6. 2024Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusioncited by 41
  7. 2024A Survey of Mambacited by 39
  8. 2024TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generationcited by 27
  9. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 27
  10. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  11. 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modelingcited by 23
  12. 2024DGMamba: Domain Generalization via Generalized State Space Modelcited by 21
38 more
  1. 2024PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learningcited by 21
  2. 2024PixOOD: Pixel-Level Out-of-Distribution Detectioncited by 20
  3. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  4. 2025OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoningcited by 18
  5. 2024Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmarkcited by 16
  6. 2024MobileMamba: Lightweight Multi-Receptive Visual Mamba Networkcited by 16
  7. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  8. 2025Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detectioncited by 11
  9. 2025M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detectioncited by 10
  10. 2024Learning Multi-view Anomaly Detection with Efficient Adaptive Selectioncited by 9
  11. 2024MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Trackingcited by 9
  12. 2025Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mambacited by 9
  13. 2025ReplayCAD: Generative Diffusion Replay for Continual Anomaly Detectioncited by 9
  14. 2025VADMamba: Exploring State Space Models for Fast Video Anomaly Detectioncited by 8
  15. 2024A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detectioncited by 7
  16. 2024MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentationcited by 7
  17. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  18. 2024Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancementcited by 6
  19. 2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
  20. 2024ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shiftcited by 5
  21. 2025CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filteringcited by 5
  22. 2025Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectorscited by 5
  23. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 4
  24. 2025Towards Personalized Quantum Federated Learning for Anomaly Detectioncited by 4
  25. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  26. 2024MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detectioncited by 3
  27. 2025UD-Mamba: A pixel-level uncertainty-driven Mamba model for medical image segmentationcited by 3
  28. 2025RoBiS: Robust Binary Segmentation for High-Resolution Industrial Imagescited by 3
  29. 2025MedVSR: Medical Video Super-Resolution with Cross State-Space Propagationcited by 3
  30. 2025UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompressioncited by 3
  31. 2025VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusioncited by 3
  32. 2026A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detectioncited by 3
  33. 2024View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesiscited by 2
  34. 2024MedSegMamba: 3D CNN-Mamba Hybrid Architecture for Brain Segmentationcited by 2
  35. 2025Salient Object Detection in Traffic Scene through the TSOD10K Datasetcited by 2
  36. 2025Omni-AD: Learning to Reconstruct Global and Local Features for Multi-class Anomaly Detectioncited by 2
  37. 2025ConMamba: Contrastive Vision Mamba for Plant Disease Detectioncited by 2
  38. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2

50 most cited of 113 All 113 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024STNMamba: Mamba-based Spatial-Temporal Normality Learning for Video Anomaly Detection
  2. 2025M2S2L: Mamba-based Multi-Scale Spatial-temporal Learning for Video Anomaly Detection
  3. 2025GLADMamba: Unsupervised Graph-Level Anomaly Detection Powered by Selective State Space Model
  4. 2025Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection
  5. 2026DMS2F-HAD: A Dual-branch Mamba-based Spatial-Spectral Fusion Network for Hyperspectral Anomaly Detection
  6. 2025Adaptive State-Space Mamba for Real-Time Sensor Data Anomaly Detection
  7. 2025SP-Mamba: Spatial-Perception State Space Model for Unsupervised Medical Anomaly Detection
  8. 2025Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection