{"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/scnet-learning-semantic-correspondence","title":"SCNet: Learning Semantic Correspondence","arxiv_id":"1705.04043","date":"2017-05-11","proceeding":"ICCV 2017 10","authors":["Kai Han","Rafael S. Rezende","Bumsub Ham","Kwan-Yee K. Wong","Minsu Cho","Cordelia Schmid","Jean Ponce"],"abstract":"This paper addresses the problem of establishing semantic correspondences\nbetween images depicting different instances of the same object or scene\ncategory. Previous approaches focus on either combining a spatial regularizer\nwith hand-crafted features, or learning a correspondence model for appearance\nonly. We propose instead a convolutional neural network architecture, called\nSCNet, for learning a geometrically plausible model for semantic\ncorrespondence. SCNet uses region proposals as matching primitives, and\nexplicitly incorporates geometric consistency in its loss function. It is\ntrained on image pairs obtained from the PASCAL VOC 2007 keypoint dataset, and\na comparative evaluation on several standard benchmarks demonstrates that the\nproposed approach substantially outperforms both recent deep learning\narchitectures and previous methods based on hand-crafted features.","url_abs":"http://arxiv.org/abs/1705.04043v3","url_pdf":"http://arxiv.org/pdf/1705.04043v3.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":"scnet-learning-semantic-correspondence","repo_url":"https://github.com/k-han/SCNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.04043","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}