{"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/how-a-general-purpose-commonsense-ontology","title":"How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval","arxiv_id":"1705.08844","date":"2017-05-24","proceeding":null,"authors":["Rodrigo Toro Icarte","Jorge A. Baier","Cristian Ruz","Alvaro Soto"],"abstract":"The knowledge representation community has built general-purpose ontologies\nwhich contain large amounts of commonsense knowledge over relevant aspects of\nthe world, including useful visual information, e.g.: \"a ball is used by a\nfootball player\", \"a tennis player is located at a tennis court\". Current\nstate-of-the-art approaches for visual recognition do not exploit these\nrule-based knowledge sources. Instead, they learn recognition models directly\nfrom training examples. In this paper, we study how general-purpose\nontologies---specifically, MIT's ConceptNet ontology---can improve the\nperformance of state-of-the-art vision systems. As a testbed, we tackle the\nproblem of sentence-based image retrieval. Our retrieval approach incorporates\nknowledge from ConceptNet on top of a large pool of object detectors derived\nfrom a deep learning technique. In our experiments, we show that ConceptNet can\nimprove performance on a common benchmark dataset. Key to our performance is\nthe use of the ESPGAME dataset to select visually relevant relations from\nConceptNet. Consequently, a main conclusion of this work is that\ngeneral-purpose commonsense ontologies improve performance on visual reasoning\ntasks when properly filtered to select meaningful visual relations.","url_abs":"http://arxiv.org/abs/1705.08844v1","url_pdf":"http://arxiv.org/pdf/1705.08844v1.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":"how-a-general-purpose-commonsense-ontology","repo_url":"https://bitbucket.org/RToroIcarte/cn-detectors","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"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}