用Mamba架构实现快速又鲁棒的局部特征匹配
MambaGlue: Fast and Robust Local Feature Matching With Mamba
- 基于Mamba设计自注意力混合模块，兼顾局部与全局上下文理解
- 引入多层感知机回归器，精准评估匹配预测的置信度
- 在多个公开数据集上实现更快推理速度与更高匹配精度
近年来，基于深度学习的鲁棒匹配方法在计算机视觉任务中得到广泛关注和改进。然而，对既鲁棒又快速的匹配技术仍存在持续需求。为此，我们提出一种基于Mamba架构的新型局部特征匹配方法——MambaGlue。Mamba是一种新兴的前沿架构，在训练和推理速度上均表现出色，且性能可媲美Transformer。具体而言，我们设计了两个模块：a) MambaAttention混合器，利用基于Mamba的自注意力结构，同时选择性地捕捉局部与全局上下文；b) 深度置信度评分回归器，采用多层感知机（MLP）架构，用于评估匹配预测与真实对应关系的置信程度。实验表明，MambaGlue在多种公开数据集上显著优于基线方法，同时保持了高效的推理速度。
原文摘要 · Abstract (English)
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 correspond to the ground-truth correspondences. Consequently, our MambaGlue achieves a balance between robustness and efficiency in real-world applications. As verified on various public datasets, we demonstrate that our MambaGlue yields a substantial performance improvement over baseline approaches while maintaining fast inference speed. Our code will be available on https://github.com/url-kaist/MambaGlue
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。