Papers › Retrieval Augmented Visual Question Answering with Outside Knowledge
Retrieval Augmented Visual Question Answering with Outside Knowledge
Weizhe Lin, Bill Byrne
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2210.03809", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2210.03809")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Retrieval | OK-VQA | RA-VQA | Recall@5 | 82.84 | #2 of 2 | Archive leaderboard | report |
| Visual Question Answering (VQA) | OK-VQA | RA-VQA (T5-large) | Accuracy | 54.48 | #14 of 37 | Archive leaderboard | report |
| Visual Question Answering (VQA) | OK-VQA | RA-VQA (T5-large) | Exact Match (EM) | 59.41 | #14 of 37 | Archive leaderboard | report |
| Visual Question Answering (VQA) | OK-VQA | RA-VQA (T5-large) | Recall@5 | 82.84 | #14 of 37 | Archive leaderboard | report |
| Visual Question Answering (VQA) | OK-VQA | RA-VQA-FrDPR (T5-large) | Accuracy | 51.22 | #17 of 37 | Archive leaderboard | report |
| Visual Question Answering (VQA) | OK-VQA | RA-VQA-FrDPR (T5-large) | Exact Match (EM) | 55.77 | #17 of 37 | Archive leaderboard | report |
| Visual Question Answering (VQA) | OK-VQA | RA-VQA-FrDPR (T5-large) | Recall@5 | 81.25 | #17 of 37 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections