{"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/collaborative-receptive-field-learning","title":"Collaborative Receptive Field Learning","arxiv_id":"1402.0170","date":"2014-02-02","proceeding":null,"authors":["Shu Kong","Zhuolin Jiang","Qiang Yang"],"abstract":"The challenge of object categorization in images is largely due to arbitrary\ntranslations and scales of the foreground objects. To attack this difficulty,\nwe propose a new approach called collaborative receptive field learning to\nextract specific receptive fields (RF's) or regions from multiple images, and\nthe selected RF's are supposed to focus on the foreground objects of a common\ncategory. To this end, we solve the problem by maximizing a submodular function\nover a similarity graph constructed by a pool of RF candidates. However,\nmeasuring pairwise distance of RF's for building the similarity graph is a\nnontrivial problem. Hence, we introduce a similarity metric called\npyramid-error distance (PED) to measure their pairwise distances through\nsumming up pyramid-like matching errors over a set of low-level features.\nBesides, in consistent with the proposed PED, we construct a simple\nnonparametric classifier for classification. Experimental results show that our\nmethod effectively discovers the foreground objects in images, and improves\nclassification performance.","url_abs":"http://arxiv.org/abs/1402.0170v1","url_pdf":"http://arxiv.org/pdf/1402.0170v1.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":"collaborative-receptive-field-learning","repo_url":"https://github.com/aimerykong/coRFL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object-categorization","task_name":"Object Categorization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}