LoFLAT：基于聚焦线性注意力Transformer的局部特征匹配
LoFLAT: Local Feature Matching using Focused Linear Attention Transformer
AI总结：
针对现有基于Transformer的无检测器局部特征匹配方法计算复杂度高、难捕捉精细局部交互的问题，提出含聚焦线性注意力的LoFLAT方法，通过三大模块实现匹配，在效率与精度上均优于LoFTR。
摘要：
局部特征匹配是图像匹配中的核心技术，在众多基于视觉的应用中发挥着关键作用。然而，现有基于Transformer的无检测器局部特征匹配方法因注意力机制的二次计算复杂度面临挑战，在高分辨率场景下尤为突出。尽管这类方法已通过线性注意力机制降低了计算成本，但仍难以捕捉精细的局部交互，影响了精确局部对应关系的准确性与鲁棒性。为在保持低计算复杂度的同时增强注意力机制的表征能力，本文提出LoFLAT——一种基于聚焦线性注意力Transformer的新型局部特征匹配方法。LoFLAT包含三大核心模块：特征提取模块、特征Transformer模块与匹配模块。具体而言，特征提取模块首先利用ResNet与特征金字塔网络（Feature Pyramid Network）提取分层特征；特征Transformer模块进一步采用聚焦线性注意力，通过聚焦映射函数优化注意力分布，并借助深度卷积增强特征多样性；最后，匹配模块通过由粗到细的策略预测准确且鲁棒的匹配结果。大量实验评估表明，所提出的LoFLAT在效率与准确性上均优于LoFTR方法。
英文摘要：
Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges due to the quadratic computational complexity of attention mechanisms, especially at high resolutions. However, while existing Transformer-based detector-free local feature matching methods have reduced computational costs using linear attention mechanisms, they still struggle to capture detailed local interactions, which affects the accuracy and robustness of precise local correspondences. In order to enhance representations of attention mechanisms while preserving low computational complexity, we propose the LoFLAT, a novel Local Feature matching using Focused Linear Attention Transformer in this paper. Our LoFLAT consists of three main modules: the Feature Extraction Module, the Feature Transformer Module, and the Matching Module. Specifically, the Feature Extraction Module firstly uses ResNet and a Feature Pyramid Network to extract hierarchical features. The Feature Transformer Module further employs the Focused Linear Attention to refine attention distribution with a focused mapping function and to enhance feature diversity with a depth-wise convolution. Finally, the Matching Module predicts accurate and robust matches through a coarse-to-fine strategy. Extensive experimental evaluations demonstrate that the proposed LoFLAT outperforms the LoFTR method in terms of both efficiency and accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
