MambaGlue: Fast and Robust Local Feature Matching With Mamba
Kihwan Ryoo, Hyungtae Lim, Hyun Myung

TL;DR
MambaGlue introduces a fast, robust local feature matching method leveraging Mamba architecture, combining local-global context understanding and confidence scoring to outperform baselines in efficiency and accuracy.
Contribution
The paper presents MambaGlue, a novel local feature matching approach that integrates Mamba-based self-attention and confidence scoring for improved speed and robustness.
Findings
Significant performance improvement over baseline methods.
Maintains fast inference speed in real-world datasets.
Balances robustness and efficiency effectively.
Abstract
In recent years, robust matching methods using deep learning-based approaches have been actively studied and improved in computer vision tasks. However, there remains a persistent demand for both robust and fast matching techniques. To address this, we propose a novel Mamba-based local feature matching approach, called MambaGlue, where Mamba is an emerging state-of-the-art architecture rapidly gaining recognition for its superior speed in both training and inference, and promising performance compared with Transformer architectures. In particular, we propose two modules: a) MambaAttention mixer to simultaneously and selectively understand the local and global context through the Mamba-based self-attention structure and b) deep confidence score regressor, which is a multi-layer perceptron (MLP)-based architecture that evaluates a score indicating how confidently matching predictions…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition
MethodsAttention Is All You Need · Label Smoothing · Layer Normalization · Linear Layer · Byte Pair Encoding · Dense Connections · Residual Connection · Multi-Head Attention · Position-Wise Feed-Forward Layer · Mamba: Linear-Time Sequence Modeling with Selective State Spaces
