{"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/srn-side-output-residual-network-for-object-1","title":"SRN: Side-output Residual Network for Object Symmetry Detection in the Wild","arxiv_id":"1703.02243","date":"2017-03-07","proceeding":"CVPR 2017 7","authors":["Wei Ke","Jie Chen","Jianbin Jiao","Guoying Zhao","Qixiang Ye"],"abstract":"In this paper, we establish a baseline for object symmetry detection in\ncomplex backgrounds by presenting a new benchmark and an end-to-end deep\nlearning approach, opening up a promising direction for symmetry detection in\nthe wild. The new benchmark, named Sym-PASCAL, spans challenges including\nobject diversity, multi-objects, part-invisibility, and various complex\nbackgrounds that are far beyond those in existing datasets. The proposed\nsymmetry detection approach, named Side-output Residual Network (SRN),\nleverages output Residual Units (RUs) to fit the errors between the object\nsymmetry groundtruth and the outputs of RUs. By stacking RUs in a\ndeep-to-shallow manner, SRN exploits the 'flow' of errors among multiple scales\nto ease the problems of fitting complex outputs with limited layers,\nsuppressing the complex backgrounds, and effectively matching object symmetry\nof different scales. Experimental results validate both the benchmark and its\nchallenging aspects related to realworld images, and the state-of-the-art\nperformance of our symmetry detection approach. The benchmark and the code for\nSRN are publicly available at https://github.com/KevinKecc/SRN.","url_abs":"http://arxiv.org/abs/1703.02243v2","url_pdf":"http://arxiv.org/pdf/1703.02243v2.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":"srn-side-output-residual-network-for-object-1","repo_url":"https://github.com/KevinKecc/SRN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"object","task_name":"Object"},{"task_slug":"symmetry-detection","task_name":"Symmetry Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}