mlsanityData to 13 Oct 2026

Hybrid Mamba for Few-Shot Segmentation

arXiv 2409.19613 ↗First posted 29 Sep 2024cs.CVcited by 21

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

Abstract (arXiv)

Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the complexity is only linear. Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS. A simple idea is to scan on support features to selectively compress them into the hidden state, which is then used as the initial hidden state to sequentially scan query features. Nevertheless, it suffers from (1) support forgetting issue: query features will also gradually be compressed when scanning on them, so the support features in hidden state keep reducing, and many query pixels cannot fuse sufficient support features; (2) intra-class gap issue: query FG is essentially more similar to itself rather than to support FG, i.e., query may prefer not to fuse support features but their own ones from the hidden state, yet the success of FSS relies on the effective use of support information. To tackle them, we design a hybrid Mamba network (HMNet), including (1) a support recapped Mamba to periodically recap the support features when scanning query, so the hidden state can always contain rich support information; (2) a query intercepted Mamba to forbid the mutual interactions among query pixels, and encourage them to fuse more support features from the hidden state. Consequently, the support information is better utilized, leading to better performance. Extensive experiments have been conducted on two public benchmarks, showing the superiority of HMNet. The code is available at https://github.com/Sam1224/HMNet.

Key facts. Cited by 21 papers in the map (data through 13 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 29 Sep 2024.

Builds on

58 of 69 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation5 Apr
  2. 2024ReMamber: Referring Image Segmentation with Mamba Twister26 Mar
  3. 2024Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference21 Mar
  4. 2024VL-Mamba: Exploring State Space Models for Multimodal Learning20 Mar
  5. 2024Pan-Mamba: Effective pan-sharpening with State Space Model19 Feb
  6. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 52

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,849
  7. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,658
  8. 2016Pyramid Scene Parsing Networkcited by 2,474
  9. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,440
  10. 2016Matching Networks for One Shot Learningcited by 2,251
  11. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,961
  12. 2024VMamba: Visual State Space Modelcited by 963
38 more
  1. 2022Simplified State Space Layers for Sequence Modelingcited by 781
  2. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 495
  3. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  4. 2017One-Shot Learning for Semantic Segmentationcited by 337
  5. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  6. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
  7. 2022Long Range Language Modeling via Gated State Spacescited by 265
  8. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  9. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  10. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  11. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  12. 2014Simultaneous Detection and Segmentationcited by 158
  13. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  14. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  15. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  16. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  17. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  18. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  19. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  20. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  21. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  22. 2021Learning Statistical Texture for Semantic Segmentationcited by 50
  23. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  24. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  25. 2024nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Modelcited by 45
  26. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  27. 2023Continual Semantic Segmentation with Automatic Memory Sample Selectioncited by 39
  28. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  29. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  30. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  31. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  32. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  33. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  34. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  35. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  36. 2024Discrete Latent Perspective Learning for Segmentation and Detectioncited by 16
  37. 2023Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentationcited by 13
  38. 2023Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancementcited by 10

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 11; 2026: 9.

21 papers.

Sort:

By area:

  1. 2025POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentationcited by 22
  2. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understandingcited by 20
  3. 2025Unlocking the Power of SAM 2 for Few-Shot Segmentationcited by 11
  4. 2025SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentationcited by 8
  5. 2026Few-Shot Semantic Segmentation Meets SAM3cited by 3
  6. 2025How Can Mamba Learn In Context with Outliers and Generalize Provably?cited by 2
  7. 2026NeuroSeg Meets DINOv3: Transferring 2D Self-Supervised Visual Priors to 3D Neuron Segmentation via DINOv3 Initializationcited by 2
  8. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelationcited by 1
  9. 2025ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentationcited by 1
  10. 2025Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentationcited by 1
  11. 2025Object-level Correlation for Few-Shot Segmentationcited by 1
  12. 2025Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentationcited by 1
9 more
  1. 2026Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsificationcited by 1
  2. 2026Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentationcited by 1
  3. 2025Inter- and Intra-image Refinement for Few Shot Segmentationcited by 0
  4. 2025Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentationcited by 0
  5. 2026Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbationscited by 0
  6. 2026Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationcited by 0
  7. 2026RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba for Few-Shot Brain Tumor Segmentationcited by 0
  8. 2026GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generationcited by 0
  9. 2026Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024S3-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation
  2. 2024MambaOut: Do We Really Need Mamba for Vision?
  3. 2024Visual Mamba: A Survey and New Outlooks
  4. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentation
  5. 2025MambaVesselNet++: A Hybrid CNN-Mamba Architecture for Medical Image Segmentation
  6. 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation
  7. 2024LoG-VMamba: Local-Global Vision Mamba for Medical Image Segmentation
  8. 2025MambaCAFU: Hybrid Multi-Scale and Multi-Attention Model with Mamba-Based Fusion for Medical Image Segmentation