{"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/greedy-gradient-ensemble-for-robust-visual","title":"Greedy Gradient Ensemble for Robust Visual Question Answering","arxiv_id":"2107.12651","date":"2021-07-27","proceeding":"ICCV 2021 10","authors":["Xinzhe Han","Shuhui Wang","Chi Su","Qingming Huang","Qi Tian"],"abstract":"Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information. As a result, they suffer from performance drop on out-of-distribution data and inadequate visual explanation. Based on experimental analysis for existing robust VQA methods, we stress the language bias in VQA that comes from two aspects, i.e., distribution bias and shortcut bias. We further propose a new de-bias framework, Greedy Gradient Ensemble (GGE), which combines multiple biased models for unbiased base model learning. With the greedy strategy, GGE forces the biased models to over-fit the biased data distribution in priority, thus makes the base model pay more attention to examples that are hard to solve by biased models. The experiments demonstrate that our method makes better use of visual information and achieves state-of-the-art performance on diagnosing dataset VQA-CP without using extra annotations.","url_abs":"https://arxiv.org/abs/2107.12651v4","url_pdf":"https://arxiv.org/pdf/2107.12651v4.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":"greedy-gradient-ensemble-for-robust-visual","repo_url":"https://github.com/GeraldHan/GGE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":[{"leaderboard":"/sota/visual-question-answering-on-vqa-cp","task":"Visual Question Answering (VQA)","dataset":"VQA-CP","model":"GGE-DQ","rank_in_archive_order":2,"of":10,"metrics":{"Score":"57.32"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.12651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12651"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/GeraldHan/GGE","reach":null}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9b1feda043480c9b","entry":"GreedyGradient","repo":"GeraldHan/GGE","repo_kind":"official","path":"vqa_debias_loss_functions.py","file_url":"https://github.com/GeraldHan/GGE/blob/HEAD/vqa_debias_loss_functions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b1feda043480c9b"}},{"code_sha256_prefix":"73c824c2bbcb9727","entry":"DebiasLossFn","repo":"GeraldHan/GGE","repo_kind":"official","path":"vqa_debias_loss_functions.py","file_url":"https://github.com/GeraldHan/GGE/blob/HEAD/vqa_debias_loss_functions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73c824c2bbcb9727"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}