{"type":"ScholarlyArticle","title":"Adaptive Edge Attention for Graph Matching with Outliers","authors":[{"name":"Jingwei Qu","slug":"jingwei-qu","given":"Jingwei","family":"Qu","affiliation":""},{"name":"Haibin Ling","slug":"haibin-ling","given":"Haibin","family":"Ling","affiliation":""},{"name":"Chenrui Zhang","slug":"chenrui-zhang","given":"Chenrui","family":"Zhang","affiliation":""},{"name":"Xiaoqing Lyu","slug":"xiaoqing-lyu","given":"Xiaoqing","family":"Lyu","affiliation":""},{"name":"Zhi Tang","slug":"zhi-tang","given":"Zhi","family":"Tang","affiliation":""}],"abstract":"Graph matching aims at establishing correspondence between node sets of given graphs while keeping the consistency between their edge sets. However, outliers in practical scenarios and equivalent learning of edge representations in deep learning methods are still challenging. To address these issues, we present an Edge Attention-adaptive Graph Matching (EAGM) network and a novel description of edge features. EAGM transforms the matching relation between two graphs into a node and edge classification problem over their assignment graph. To explore the potential of edges, EAGM learns edge attention on the assignment graph to 1) reveal the impact of each edge on graph matching, as well as 2) adjust the learning of edge representations adaptively. To alleviate issues caused by the outliers, we describe an edge by aggregating the semantic information over the space spanned by the edge. Such rich information provides clear distinctions between different edges (e.g., inlier-inlier edges vs. inlier-outlier edges), which further distinguishes outliers in the view of their associated edges. Extensive experiments demonstrate that EAGM achieves promising matching quality compared with state-of-the-arts, on cases both with and without outliers. Our source code along with the experiments is available at https://github.com/bestwei/EAGM.","doi":"10.24963/ijcai.2021/134","url":"https://ijcai.org/proceedings/2021/134","pdf":"https://ijcai.org/proceedings/2021/0134.pdf","markdown":"https://ijcai.org/proceedings/2021/134.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/134","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Computer Vision I","track":"Main Track","number":134,"pages":{"first":966,"last":972},"keywords":["Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Machine Learning: Deep Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}