{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/retrieval-augmented-visual-question-answering","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","arxiv_id":"2210.03809","date":"2022-10-07","proceeding":null,"authors":["Weizhe Lin","Bill Byrne"],"abstract":"Outside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQA task that requires retrieval of external knowledge to answer questions about images. Recent OK-VQA systems use Dense Passage Retrieval (DPR) to retrieve documents from external knowledge bases, such as Wikipedia, but with DPR trained separately from answer generation, introducing a potential limit on the overall system performance. Instead, we propose a joint training scheme which includes differentiable DPR integrated with answer generation so that the system can be trained in an end-to-end fashion. Our experiments show that our scheme outperforms recent OK-VQA systems with strong DPR for retrieval. We also introduce new diagnostic metrics to analyze how retrieval and generation interact. The strong retrieval ability of our model significantly reduces the number of retrieved documents needed in training, yielding significant benefits in answer quality and computation required for training.","url_abs":"https://arxiv.org/abs/2210.03809v2","url_pdf":"https://arxiv.org/pdf/2210.03809v2.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":"retrieval-augmented-visual-question-answering","repo_url":"https://github.com/linweizhedragon/retrieval-augmented-visual-question-answering","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"answer-generation","task_name":"Answer Generation"},{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"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/retrieval-on-ok-vqa","task":"Retrieval","dataset":"OK-VQA","model":"RA-VQA","rank_in_archive_order":2,"of":2,"metrics":{"Recall@5":"82.84"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"RA-VQA (T5-large)","rank_in_archive_order":14,"of":37,"metrics":{"Accuracy":"54.48","Exact Match (EM)":"59.41","Recall@5":"82.84"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"RA-VQA-FrDPR (T5-large)","rank_in_archive_order":17,"of":37,"metrics":{"Accuracy":"51.22","Exact Match (EM)":"55.77","Recall@5":"81.25"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.03809","atlas_url":"https://app.syntology.ai/?focus=2210.03809","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2210.03809"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.03809\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.03809"},"call":"get_concepts_for_paper(arxiv_id=\"2210.03809\")"}],"by_repo":[{"repo":"linweizhedragon/retrieval-augmented-visual-question-answering","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2309.17133"],"harvested_for_calls":[{"arxiv_id":"2309.17133","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.17133"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.17133\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"29bc7b0087fd2544bd8843d92c3df9f7e40205906e39ef75409dc8170740e4ee","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}