{"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/raven-a-dataset-for-relational-and-analogical","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","arxiv_id":"1903.02741","date":"2019-03-07","proceeding":"CVPR 2019 6","authors":["Chi Zhang","Feng Gao","Baoxiong Jia","Yixin Zhu","Song-Chun Zhu"],"abstract":"Dramatic progress has been witnessed in basic vision tasks involving\nlow-level perception, such as object recognition, detection, and tracking.\nUnfortunately, there is still an enormous performance gap between artificial\nvision systems and human intelligence in terms of higher-level vision problems,\nespecially ones involving reasoning. Earlier attempts in equipping machines\nwith high-level reasoning have hovered around Visual Question Answering (VQA),\none typical task associating vision and language understanding. In this work,\nwe propose a new dataset, built in the context of Raven's Progressive Matrices\n(RPM) and aimed at lifting machine intelligence by associating vision with\nstructural, relational, and analogical reasoning in a hierarchical\nrepresentation. Unlike previous works in measuring abstract reasoning using\nRPM, we establish a semantic link between vision and reasoning by providing\nstructure representation. This addition enables a new type of abstract\nreasoning by jointly operating on the structure representation. Machine\nreasoning ability using modern computer vision is evaluated in this newly\nproposed dataset. Additionally, we also provide human performance as a\nreference. Finally, we show consistent improvement across all models by\nincorporating a simple neural module that combines visual understanding and\nstructure reasoning.","url_abs":"http://arxiv.org/abs/1903.02741v1","url_pdf":"http://arxiv.org/pdf/1903.02741v1.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":[],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[{"slug":"raven","name":"RAVEN","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.02741","atlas_url":"https://app.syntology.ai/?focus=1903.02741","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}