Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
European Conference on Computer Vision(2020)
摘要
Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers. Using the presence of heavily optimized combinatorial solvers together with some improvements in architecture design, we advance state-of-the-art on deep graph matching benchmarks for keypoint correspondence. In addition, we highlight the conceptual advantages of incorporating solvers into deep learning architectures, such as the possibility of post-processing with a strong multi-graph matching solver or the indifference to changes in the training setting. Finally, we propose two new challenging experimental setups.
更多查看译文
关键词
Deep graph matching,Keypoint correspondence,Combinatorial optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络