{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/transformatcher-match-to-match-attention-for","title":"TransforMatcher: Match-to-Match Attention for Semantic Correspondence","arxiv_id":"2205.11634","date":"2022-05-23","proceeding":"CVPR 2022 1","authors":["SeungWook Kim","Juhong Min","Minsu Cho"],"abstract":"Establishing correspondences between images remains a challenging task, especially under large appearance changes due to different viewpoints or intra-class variations. In this work, we introduce a strong semantic image matching learner, dubbed TransforMatcher, which builds on the success of transformer networks in vision domains. Unlike existing convolution- or attention-based schemes for correspondence, TransforMatcher performs global match-to-match attention for precise match localization and dynamic refinement. To handle a large number of matches in a dense correlation map, we develop a light-weight attention architecture to consider the global match-to-match interactions. We also propose to utilize a multi-channel correlation map for refinement, treating the multi-level scores as features instead of a single score to fully exploit the richer layer-wise semantics. In experiments, TransforMatcher sets a new state of the art on SPair-71k while performing on par with existing SOTA methods on the PF-PASCAL dataset.","url_abs":"https://arxiv.org/abs/2205.11634v1","url_pdf":"https://arxiv.org/pdf/2205.11634v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"transformatcher-match-to-match-attention-for","repo_url":"https://github.com/wookiekim/transformatcher","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset":"SPair-71k","model":"TransforMatcher","rank_in_archive_order":14,"of":22,"metrics":{"PCK":"53.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.11634","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}