Joint Graph Learning and Matching for Semantic Feature Correspondence
作者：
Highlights：
• We analyze shortcomings of graph construction strategies in previous algorithms.
• We propose to boost graph matching by learning reliable graph patterns without input graph structures.
• We integrate the learning of graph structures, node representations and matching decisions into a unified framework.
• We provide insightful analysis and discussion about the effectiveness of learnt graph patterns.
摘要
•We analyze shortcomings of graph construction strategies in previous algorithms.•We propose to boost graph matching by learning reliable graph patterns without input graph structures.•We integrate the learning of graph structures, node representations and matching decisions into a unified framework.•We provide insightful analysis and discussion about the effectiveness of learnt graph patterns.
论文关键词：Feature correspondence,Attention network,Graph matching,Graph learning
论文评审过程：Received 14 March 2022, Revised 22 August 2022, Accepted 20 September 2022, Available online 25 September 2022, Version of Record 29 September 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.109059
