{"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/fcss-fully-convolutional-self-similarity-for","title":"FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence","arxiv_id":"1702.00926","date":"2017-02-03","proceeding":"CVPR 2017 7","authors":["Seungryong Kim","Dongbo Min","Bumsub Ham","Sangryul Jeon","Stephen Lin","Kwanghoon Sohn"],"abstract":"We present a descriptor, called fully convolutional self-similarity (FCSS),\nfor dense semantic correspondence. To robustly match points among different\ninstances within the same object class, we formulate FCSS using local\nself-similarity (LSS) within a fully convolutional network. In contrast to\nexisting CNN-based descriptors, FCSS is inherently insensitive to intra-class\nappearance variations because of its LSS-based structure, while maintaining the\nprecise localization ability of deep neural networks. The sampling patterns of\nlocal structure and the self-similarity measure are jointly learned within the\nproposed network in an end-to-end and multi-scale manner. As training data for\nsemantic correspondence is rather limited, we propose to leverage object\ncandidate priors provided in existing image datasets and also correspondence\nconsistency between object pairs to enable weakly-supervised learning.\nExperiments demonstrate that FCSS outperforms conventional handcrafted\ndescriptors and CNN-based descriptors on various benchmarks.","url_abs":"http://arxiv.org/abs/1702.00926v1","url_pdf":"http://arxiv.org/pdf/1702.00926v1.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":"fcss-fully-convolutional-self-similarity-for","repo_url":"https://github.com/seungryong/FCSS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.00926","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}