基于种子图匹配网络的特征匹配学习
Learning to Match Features with Seeded Graph Matching Network
摘要：
跨图像的局部特征匹配是计算机视觉中的一个基本问题。以高精度和高效率为目标，提出了种子图匹配网络（Seeded Graph Matching Network，简称SENN），这是一种具有稀疏结构的图神经网络，用于减少冗余连接和学习紧凑表示。该网络由1）播种模块组成，该模块通过生成一小组可靠的匹配作为种子来对匹配进行优化。2)种子图神经网络，利用种子匹配在图像内/图像间传递消息，并预测分配成本。提出了三种新的操作作为消息传递的基本元素：1）注意力池，它聚合图像中的关键点特征以进行种子匹配。2)种子过滤，增强种子功能并在图像之间交换消息。3)Attentional Unpooling，将种子特征传播回原始关键点。实验表明，我们的方法降低了计算和内存的复杂性显着相比，典型的基于注意力的网络，同时实现竞争力或更高的性能。
英文摘要：
Matching local features across images is a fundamental problem in computer vision. Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching Network, a graph neural network with sparse structure to reduce redundant connectivity and learn compact representation. The network consists of 1) Seeding Module, which initializes the matching by generating a small set of reliable matches as seeds. 2) Seeded Graph Neural Network, which utilizes seed matches to pass messages within/across images and predicts assignment costs. Three novel operations are proposed as basic elements for message passing: 1) Attentional Pooling, which aggregates keypoint features within the image to seed matches. 2) Seed Filtering, which enhances seed features and exchanges messages across images. 3) Attentional Unpooling, which propagates seed features back to original keypoints. Experiments show that our method reduces computational and memory complexity significantly compared with typical attention-based networks while competitive or higher performance is achieved.
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。
