{"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/mutant-a-training-paradigm-for-out-of","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","arxiv_id":"2009.08566","date":"2020-09-18","proceeding":"EMNLP 2020 11","authors":["Tejas Gokhale","Pratyay Banerjee","Chitta Baral","Yezhou Yang"],"abstract":"While progress has been made on the visual question answering leaderboards, models often utilize spurious correlations and priors in datasets under the i.i.d. setting. As such, evaluation on out-of-distribution (OOD) test samples has emerged as a proxy for generalization. In this paper, we present MUTANT, a training paradigm that exposes the model to perceptually similar, yet semantically distinct mutations of the input, to improve OOD generalization, such as the VQA-CP challenge. Under this paradigm, models utilize a consistency-constrained training objective to understand the effect of semantic changes in input (question-image pair) on the output (answer). Unlike existing methods on VQA-CP, MUTANT does not rely on the knowledge about the nature of train and test answer distributions. MUTANT establishes a new state-of-the-art accuracy on VQA-CP with a $10.57\\%$ improvement. Our work opens up avenues for the use of semantic input mutations for OOD generalization in question answering.","url_abs":"https://arxiv.org/abs/2009.08566v2","url_pdf":"https://arxiv.org/pdf/2009.08566v2.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":"mutant-a-training-paradigm-for-out-of","repo_url":"https://github.com/tejasG53/vqa_mutant","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mutant-a-training-paradigm-for-out-of","repo_url":"https://github.com/tejas-gokhale/vqa_mutant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"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)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.08566","atlas_url":"https://app.syntology.ai/?focus=2009.08566","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}