# Hybrid Mamba for Few-Shot Segmentation

arXiv: https://arxiv.org/abs/2409.19613 · HTML: https://mlsanity.com/paper/2409.19613/

## Key facts

- Cited by 21 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 29 Sep 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 30 of 58)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation](https://mlsanity.com/paper/2401.13560/) (2024)
- [Long Range Language Modeling via Gated State Spaces](https://mlsanity.com/paper/2206.13947/) (2022)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [Feature Weighting and Boosting for Few-Shot Segmentation](https://mlsanity.com/paper/1909.13140/) (2019)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [Simultaneous Detection and Segmentation](https://mlsanity.com/paper/1407.1808/) (2014)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Few-Shot Segmentation via Cycle-Consistent Transformer](https://mlsanity.com/paper/2106.02320/) (2021)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)
- [Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference](https://mlsanity.com/paper/2403.14520/) (2024)

## Built on by (most cited first, 21 of 21)

- [POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation](https://mlsanity.com/paper/2504.00640/) (2025)
- [Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding](https://mlsanity.com/paper/2411.08516/) (2024)
- [Unlocking the Power of SAM 2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.14100/) (2025)
- [SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.21795/) (2025)
- [Few-Shot Semantic Segmentation Meets SAM3](https://mlsanity.com/paper/2604.05433/) (2026)
- [How Can Mamba Learn In Context with Outliers and Generalize Provably?](https://mlsanity.com/paper/2510.00399/) (2025)
- [NeuroSeg Meets DINOv3: Transferring 2D Self-Supervised Visual Priors to 3D Neuron Segmentation via DINOv3 Initialization](https://mlsanity.com/paper/2603.23104/) (2026)
- [UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelation](https://mlsanity.com/paper/2504.15669/) (2025)
- [ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation](https://mlsanity.com/paper/2507.02294/) (2025)
- [Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation](https://mlsanity.com/paper/2507.19140/) (2025)
- [Object-level Correlation for Few-Shot Segmentation](https://mlsanity.com/paper/2509.07917/) (2025)
- [Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentation](https://mlsanity.com/paper/2511.15118/) (2025)
- [Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsification](https://mlsanity.com/paper/2602.05218/) (2026)
- [Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2603.05952/) (2026)
- [Inter- and Intra-image Refinement for Few Shot Segmentation](https://mlsanity.com/paper/2507.05838/) (2025)
- [Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentation](https://mlsanity.com/paper/2511.16435/) (2025)
- [Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbations](https://mlsanity.com/paper/2601.03596/) (2026)
- [Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation](https://mlsanity.com/paper/2602.05217/) (2026)
- [RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba for Few-Shot Brain Tumor Segmentation](https://mlsanity.com/paper/2607.05035/) (2026)
- [GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation](https://mlsanity.com/paper/2607.05257/) (2026)
- [Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity](https://mlsanity.com/paper/2609.25538/) (2026)

## 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.