mlsanityData to 14 Oct 2026

Similarity-Aware Selective State-Space Modeling for Semantic Correspondence

arXiv 2509.24318 ↗First posted 29 Sep 2025cs.CVcited by 1

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

Abstract (arXiv)

Establishing semantic correspondences between images is a fundamental yet challenging task in computer vision. Traditional feature-metric methods enhance visual features but may miss complex inter-correlation relationships, while recent correlation-metric approaches are hindered by high computational costs due to processing 4D correlation maps. We introduce MambaMatcher, a novel method that overcomes these limitations by efficiently modeling high-dimensional correlations using selective state-space models (SSMs). By implementing a similarity-aware selective scan mechanism adapted from Mamba's linear-complexity algorithm, MambaMatcher refines the 4D correlation map effectively without compromising feature map resolution or receptive field. Experiments on standard semantic correspondence benchmarks demonstrate that MambaMatcher achieves state-of-the-art performance.

Key facts. Cited by 1 paper 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 48 of its 59 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

48 of 59 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition26 Mar
  2. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  7. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  8. 2024VMamba: Visual State Space Modelcited by 969
  9. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  10. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
  11. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  12. 2023Emergent Correspondence from Image Diffusioncited by 446
34 more
  1. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 328
  2. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
  3. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 287
  4. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 214
  5. 2023StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-Oncited by 175
  6. 2018Neighbourhood Consensus Networkscited by 174
  7. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 146
  8. 2017Parallelizing Linear Recurrent Neural Nets Over Sequence Lengthcited by 127
  9. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  10. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 108
  11. 2024MedMamba: Vision Mamba for Medical Image Classificationcited by 88
  12. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  13. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 73
  14. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  15. 2021GAN-Supervised Dense Visual Alignmentcited by 62
  16. 2021Fastformer: Additive Attention Can Be All You Needcited by 61
  17. 2019SFNet: Learning Object-aware Semantic Correspondencecited by 60
  18. 2020Learning to Compose Hypercolumns for Visual Correspondencecited by 53
  19. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  20. 2017Proposal Flow: Semantic Correspondences from Object Proposalscited by 47
  21. 2021Convolutional Hough Matching Networkscited by 43
  22. 2020Correspondence Networks with Adaptive Neighbourhood Consensuscited by 42
  23. 2023SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matchingcited by 38
  24. 2021Multi-scale Matching Networks for Semantic Correspondencecited by 32
  25. 2022Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondencecited by 32
  26. 2018Attentive Semantic Alignment with Offset-Aware Correlation Kernelscited by 31
  27. 2022Learning Semantic Correspondence with Sparse Annotationscited by 31
  28. 2022Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondencescited by 30
  29. 2022TransforMatcher: Match-to-Match Attention for Semantic Correspondencecited by 29
  30. 2015Dense Semantic Correspondence where Every Pixel is a Classifiercited by 15
  31. 2021Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondencecited by 12
  32. 2023Efficient Semantic Matching with Hypercolumn Correlationcited by 6
  33. 2024CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondencescited by 6
  34. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Can Graphs Help Vision SSMs See Better?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks
  2. 2024Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion
  3. 2026MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
  4. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan
  5. 2025Towards Robust Semantic Correspondence: A Benchmark and Insights
  6. 2025VMatcher: State-Space Semi-Dense Local Feature Matching
  7. 2024A Survey on Visual Mamba
  8. 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model