{"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/swiden-convolutional-neural-networks-for","title":"SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition","arxiv_id":"1607.08764","date":"2016-07-29","proceeding":null,"authors":["Ravi Kiran Sarvadevabhatla","Shiv Surya","Srinivas S. S. Kruthiventi","Venkatesh Babu R"],"abstract":"Current state of the art object recognition architectures achieve impressive\nperformance but are typically specialized for a single depictive style (e.g.\nphotos only, sketches only). In this paper, we present SwiDeN : our\nConvolutional Neural Network (CNN) architecture which recognizes objects\nregardless of how they are visually depicted (line drawing, realistic shaded\ndrawing, photograph etc.). In SwiDeN, we utilize a novel `deep' depictive\nstyle-based switching mechanism which appropriately addresses the\ndepiction-specific and depiction-invariant aspects of the problem. We compare\nSwiDeN with alternative architectures and prior work on a 50-category Photo-Art\ndataset containing objects depicted in multiple styles. Experimental results\nshow that SwiDeN outperforms other approaches for the depiction-invariant\nobject recognition problem.","url_abs":"http://arxiv.org/abs/1607.08764v1","url_pdf":"http://arxiv.org/pdf/1607.08764v1.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":"swiden-convolutional-neural-networks-for","repo_url":"https://github.com/val-iisc/swiden","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"depiction-invariant-object-recognition","task_name":"Depiction Invariant Object Recognition"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depiction-invariant-object-recognition-on","task":"Depiction Invariant Object Recognition","dataset":"Photo-Art-50","model":"SwiDeN","rank_in_archive_order":1,"of":1,"metrics":{"Overall Accuracy":"93.02%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}