{"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/learning-visual-reasoning-without-strong","title":"Learning Visual Reasoning Without Strong Priors","arxiv_id":"1707.03017","date":"2017-07-10","proceeding":null,"authors":["Ethan Perez","Harm de Vries","Florian Strub","Vincent Dumoulin","Aaron Courville"],"abstract":"Achieving artificial visual reasoning - the ability to answer image-related\nquestions which require a multi-step, high-level process - is an important step\ntowards artificial general intelligence. This multi-modal task requires\nlearning a question-dependent, structured reasoning process over images from\nlanguage. Standard deep learning approaches tend to exploit biases in the data\nrather than learn this underlying structure, while leading methods learn to\nvisually reason successfully but are hand-crafted for reasoning. We show that a\ngeneral-purpose, Conditional Batch Normalization approach achieves\nstate-of-the-art results on the CLEVR Visual Reasoning benchmark with a 2.4%\nerror rate. We outperform the next best end-to-end method (4.5%) and even\nmethods that use extra supervision (3.1%). We probe our model to shed light on\nhow it reasons, showing it has learned a question-dependent, multi-step\nprocess. Previous work has operated under the assumption that visual reasoning\ncalls for a specialized architecture, but we show that a general architecture\nwith proper conditioning can learn to visually reason effectively.","url_abs":"http://arxiv.org/abs/1707.03017v5","url_pdf":"http://arxiv.org/pdf/1707.03017v5.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":"learning-visual-reasoning-without-strong","repo_url":"https://github.com/ethanjperez/film","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"learning-visual-reasoning-without-strong","repo_url":"https://github.com/GuessWhatGame/clevr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"conditional-batch-normalization","method_name":"Conditional Batch Normalization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.03017","atlas_url":"https://app.syntology.ai/?focus=1707.03017","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}