# JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba

arXiv: https://arxiv.org/abs/2503.03437 · HTML: https://mlsanity.com/paper/2503.03437/

## Key facts

- Cited by 14 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 35 of its 47 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## 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 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba](https://mlsanity.com/paper/2403.09977/) (2024)
- [MatchFormer: Interleaving Attention in Transformers for Feature Matching](https://mlsanity.com/paper/2203.09645/) (2022)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [Learning to Match Features with Seeded Graph Matching Network](https://mlsanity.com/paper/2108.08771/) (2021)
- [Dual-Resolution Correspondence Networks](https://mlsanity.com/paper/2006.08844/) (2020)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)

## Built on by (most cited first, 14 of 14)

- [EDM: Efficient Deep Feature Matching](https://mlsanity.com/paper/2503.05122/) (2025)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks](https://mlsanity.com/paper/2507.22477/) (2025)
- [MVSMamba: Multi-View Stereo with State Space Model](https://mlsanity.com/paper/2511.01315/) (2025)
- [Selecting and Pruning: A Differentiable Causal Sequentialized State-Space Model for Two-View Correspondence Learning](https://mlsanity.com/paper/2503.17938/) (2025)
- [SURE: Semi-dense Uncertainty-REfined Feature Matching](https://mlsanity.com/paper/2603.04869/) (2026)
- [Not All Pixels Are Equal: Confidence-Guided Attention for Feature Matching](https://mlsanity.com/paper/2505.02161/) (2025)
- [Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splatting](https://mlsanity.com/paper/2603.29185/) (2026)
- [Improving Local Feature Matching by Entropy-inspired Scale Adaptability and Flow-endowed Local Consistency](https://mlsanity.com/paper/2604.06713/) (2026)
- [Improving Viewpoint-Invariance and Temporal Consistency for Action Detection](https://mlsanity.com/paper/2605.22695/) (2026)
- [Cross-Modality Feature Fusion Based on Structured State Space Duality for Multimodal Image Registration Network](https://mlsanity.com/paper/2606.03341/) (2026)
- [Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives](https://mlsanity.com/paper/2608.11093/) (2026)
- [Radiation, Rotation and Scale Invariant Feature Descriptor for Multimodal Image Matching](https://mlsanity.com/paper/2609.06343/) (2026)
- [UltraMatch: Transport Path Routing for Ultra-Fast and Memory-Efficient Image Matching](https://mlsanity.com/paper/2609.36980/) (2026)

## Abstract (arXiv)

Existing state-of-the-art feature matchers capture long-range dependencies with Transformers but are hindered by high spatial complexity, leading to demanding training and highlatency inference. Striking a better balance between performance and efficiency remains a challenge in feature matching. Inspired by the linear complexity O(N) of Mamba, we propose an ultra-lightweight Mamba-based matcher, named JamMa, which converges on a single GPU and achieves an impressive performance-efficiency balance in inference. To unlock the potential of Mamba for feature matching, we propose Joint Mamba with a scan-merge strategy named JEGO, which enables: (1) Joint scan of two images to achieve high-frequency mutual interaction, (2) Efficient scan with skip steps to reduce sequence length, (3) Global receptive field, and (4) Omnidirectional feature representation. With the above properties, the JEGO strategy significantly outperforms the scan-merge strategies proposed in VMamba and EVMamba in the feature matching task. Compared to attention-based sparse and semi-dense matchers, JamMa demonstrates a superior balance between performance and efficiency, delivering better performance with less than 50% of the parameters and FLOPs.