mlsanityData to 14 Oct 2026

A Survey on Mamba Architecture for Vision Applications

arXiv 2502.07161 ↗First posted 11 Feb 2025cs.CV cs.AIcited by 8

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these limitations, the Mamba architecture utilizes state-space models (SSMs) for linear scalability, efficient processing, and improved contextual awareness. This paper investigates Mamba architecture for visual domain applications and its recent advancements, including Vision Mamba (ViM) and VideoMamba, which introduce bidirectional scanning, selective scanning mechanisms, and spatiotemporal processing to enhance image and video understanding. Architectural innovations like position embeddings, cross-scan modules, and hierarchical designs further optimize the Mamba framework for global and local feature extraction. These advancements position Mamba as a promising architecture in computer vision research and applications.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 58 of its 69 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

58 of 69 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks20 Dec
  2. 2024EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality22 Nov
  3. 2024Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion19 Oct
  4. 2024Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution14 Oct
  5. 2024Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion15 Sep
  6. 2024Neural Architecture Search based Global-local Vision Mamba for Palm-Vein Recognition11 Aug
  7. 2024VSSD: Vision Mamba with Non-Causal State Space Duality26 Jul
  8. 2024Mamba-R: Vision Mamba ALSO Needs Registers23 May
  9. 2024A Survey on Visual Mamba24 Apr
  10. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition26 Mar
  11. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan14 Mar
  12. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2017Mask R-CNNcited by 7,277
  6. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  10. 2017The Kinetics Human Action Video Datasetcited by 1,909
  11. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  12. 2021ViViT: A Video Vision Transformercited by 1,620
34 more
  1. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  2. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  3. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  4. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  5. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  6. 2022Token Merging: Your ViT But Fastercited by 1,021
  7. 2024VMamba: Visual State Space Modelcited by 969
  8. 2018Object Detection with Deep Learning: A Reviewcited by 528
  9. 2021XCiT: Cross-Covariance Image Transformerscited by 338
  10. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 328
  11. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 108
  12. 2024MedMamba: Vision Mamba for Medical Image Classificationcited by 88
  13. 2022What Makes Convolutional Models Great on Long Sequence Modeling?cited by 87
  14. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 71
  15. 2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 64
  16. 2023PuMer: Pruning and Merging Tokens for Efficient Vision Language Modelscited by 53
  17. 2024A Survey of Mambacited by 39
  18. 2024A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyondcited by 16
  19. 2024Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasetscited by 14
  20. 2023Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRIcited by 9
  21. 2020Time-aware Large Kernel Convolutionscited by 8
  22. 2024Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusioncited by 7
  23. 2024MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object Detectioncited by 6
  24. 2024FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagationcited by 5
  25. 2023Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Modelscited by 4
  26. 2024Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Modelcited by 4
  27. 2024MambaBEV: An EV-based 3D detection model with Mamba2cited by 4
  28. 2024A New Dataset and Comparative Study for Aphid Cluster Detection and Segmentation in Sorghum Fieldscited by 3
  29. 2024NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMscited by 3
  30. 2024MambaDETR: Query-based Temporal Modeling using State Space Model for Multi-View 3D Object Detectioncited by 3
  31. 2024MambaU-Lite: A Lightweight Model based on Mamba and Integrated Channel-Spatial Attention for Skin Lesion Segmentationcited by 2
  32. 2025MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videoscited by 2
  33. 2025MambaTron: Efficient Cross-Modal Point Cloud Enhancement using Aggregate Selective State Space Modelingcited by 2
  34. 2024Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mambacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insightscited by 3
  2. 2025Mamba-Based Ensemble learning for White Blood Cell Classificationcited by 1
  3. 2025UNet with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning for Medical Image Segmentationcited by 1
  4. 2025Vision-Proprioception Fusion with Mamba2 in End-to-End Reinforcement Learning for Motion Controlcited by 0
  5. 2025MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processingcited by 0
  6. 2026Beyond ZOH: Advanced Discretization Strategies for Vision Mambacited by 0
  7. 2026ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGAcited by 0
  8. 2026Following Motion for Sequential Modeling in Video Frame Interpolationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Visual Mamba: A Survey and New Outlooks
  2. 2026SF-Mamba: Rethinking State Space Model for Vision
  3. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applications
  4. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbone
  5. 2024MambaOut: Do We Really Need Mamba for Vision?
  6. 2026MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
  7. 2024Demystify Mamba in Vision: A Linear Attention Perspective
  8. 2025Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing