mlsanityData to 14 Oct 2026

PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition

arXiv 2403.17695 ↗First posted 26 Mar 2024cs.CV cs.LGcited by 141

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

Abstract (arXiv)

We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial attempts have been made to apply it to images. In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images by (i) a continuous 2D scanning process that improves spatial continuity by ensuring adjacency of tokens in the scanning sequence, and (ii) direction-aware updating which enables the model to discern the spatial relations of tokens by encoding directional information. Our architecture is designed to be easy to use and easy to scale, formed by stacking identical PlainMamba blocks, resulting in a model with constant width throughout all layers. The architecture is further simplified by removing the need for special tokens. We evaluate PlainMamba on a variety of visual recognition tasks, achieving performance gains over previous non-hierarchical models and is competitive with hierarchical alternatives. For tasks requiring high-resolution inputs, in particular, PlainMamba requires much less computing while maintaining high performance. Code and models are available at: https://github.com/ChenhongyiYang/PlainMamba .

Key facts. Cited by 141 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 95 of its 107 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

95 of 107 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba15 Mar
  2. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan14 Mar
  3. 2024Pan-Mamba: Effective pan-sharpening with State Space Model19 Feb
  4. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 91

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  5. 2020Language Models are Few-Shot Learnerscited by 32,419
  6. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  7. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  8. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  9. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  10. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  11. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  12. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
38 more
  1. 2023Segment Anythingcited by 8,234
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2017Mask R-CNNcited by 7,277
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  10. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  11. 2017Squeeze-and-Excitation Networkscited by 4,789
  12. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  13. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  14. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  15. 2014Going Deeper with Convolutionscited by 4,241
  16. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  17. 2022A ConvNet for the 2020scited by 3,579
  18. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  19. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  20. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  21. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  22. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  23. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  24. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  25. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  26. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  27. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  28. 2017Random Erasing Data Augmentationcited by 1,239
  29. 2021Scaling Vision Transformerscited by 999
  30. 2024VMamba: Visual State Space Modelcited by 969
  31. 2020Designing Network Design Spacescited by 960
  32. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  33. 2021Multiscale Vision Transformerscited by 897
  34. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  35. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  36. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  37. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  38. 2023Retentive Network: A Successor to Transformer for Large Language Modelscited by 613

50 most cited of 91 All 91 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 56; 2025: 55; 2026: 30.

141 papers.

Sort:

By area:

  1. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 143
  2. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 103
  3. 2024Demystify Mamba in Vision: A Linear Attention Perspectivecited by 102
  4. 2024UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animationcited by 102
  5. 2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 64
  6. 2024Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Modelcited by 62
  7. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  8. 2024Vision Mamba: A Comprehensive Survey and Taxonomycited by 54
  9. 2024A Survey on Visual Mambacited by 50
  10. 2024CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detectioncited by 48
  11. 2024Visual Mamba: A Survey and New Outlookscited by 41
  12. 2024Mamba-R: Vision Mamba ALSO Needs Registerscited by 41
38 more
  1. 2024Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusioncited by 41
  2. 2024A Survey of Mambacited by 39
  3. 2024VSSD: Vision Mamba with Non-Causal State Space Dualitycited by 29
  4. 2024Exploring Token Pruning in Vision State Space Modelscited by 28
  5. 2025Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And Morecited by 28
  6. 2024Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Studycited by 24
  7. 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modelingcited by 23
  8. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
  9. 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Modelcited by 18
  10. 2025DefMamba: Deformable Visual State Space Modelcited by 18
  11. 2024EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Dualitycited by 17
  12. 2024A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyondcited by 16
  13. 2024MobileMamba: Lightweight Multi-Receptive Visual Mamba Networkcited by 16
  14. 2025SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structurescited by 16
  15. 2024SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networkscited by 14
  16. 2024ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attentioncited by 13
  17. 2024GrootVL: Tree Topology is All You Need in State Space Modelcited by 13
  18. 2024SUM: Saliency Unification through Mamba for Visual Attention Modelingcited by 12
  19. 2024Scalable Visual State Space Model with Fractal Scanningcited by 11
  20. 2024PTQ4VM: Post-Training Quantization for Visual Mambacited by 10
  21. 2025Animate-X++: Universal Character Image Animation with Dynamic Backgroundscited by 10
  22. 2024Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiencycited by 9
  23. 2025DAMamba: Vision State Space Model with Dynamic Adaptive Scancited by 9
  24. 2024Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domaincited by 8
  25. 2025A Survey on Mamba Architecture for Vision Applicationscited by 8
  26. 2024LFMamba: Light Field Image Super-Resolution with State Space Modelcited by 7
  27. 2024OPa-Ma: Text Guided Mamba for 360-degree Image Out-paintingcited by 7
  28. 2024MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentationcited by 7
  29. 2024MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrievalcited by 7
  30. 2024Deformable Mamba for Wide Field of View Segmentationcited by 7
  31. 2025UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weakencited by 7
  32. 2024V2M: Visual 2-Dimensional Mamba for Image Representation Learningcited by 6
  33. 2024Topology-aware Mamba for Crack Segmentation in Structurescited by 6
  34. 2025TransMamba: Fast Universal Architecture Adaption from Transformers to Mambacited by 6
  35. 2025Dynamic Vision Mambacited by 6
  36. 2025Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlookcited by 6
  37. 2025MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recoverycited by 6
  38. 2024Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-trainingcited by 5

50 most cited of 141 All 141 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 20242DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
  2. 2024VideoMamba: Spatio-Temporal Selective State Space Model
  3. 2024GroupMamba: Efficient Group-Based Visual State Space Model
  4. 2026SF-Mamba: Rethinking State Space Model for Vision
  5. 2024Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution
  6. 2024StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos
  7. 2024VideoMamba: State Space Model for Efficient Video Understanding
  8. 2024Computation-Efficient Era: A Comprehensive Survey of State Space Models in Medical Image Analysis