Papers › Bilinear Attention Networks

Bilinear Attention Networks

21 May 2018NeurIPS 2018 12arXiv:1805.07932archive 2025-07-28

Jin-Hwa Kim, Jaehyun Jun, Byoung-Tak Zhang

Attention networks in multimodal learning provide an efficient way to utilize given visual information selectively. However, the computational cost to learn attention distributions for every pair of multimodal input channels is prohibitively expensive. To solve this problem, co-attention builds two separate attention distributions for each modality neglecting the interaction between multimodal inputs. In this paper, we propose bilinear attention networks (BAN) that find bilinear attention distributions to utilize given vision-language information seamlessly. BAN considers bilinear interactions among two groups of input channels, while low-rank bilinear pooling extracts the joint representations for each pair of channels. Furthermore, we propose a variant of multimodal residual networks to exploit eight-attention maps of the BAN efficiently. We quantitatively and qualitatively evaluate our model on visual question answering (VQA 2.0) and Flickr30k Entities datasets, showing that BAN significantly outperforms previous methods and achieves new state-of-the-arts on both datasets.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1805.07932")

Code

Syntology Ran 4 of 13 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · violated contract.

By repository: official repository: 7 samples from 1 repository, 3 ran; community (archive-listed): 6 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jnhwkim/ban-vqa officialmentioned on GitHubpytorchMIT report
Cyanogenoid/vqa-counting mentioned on GitHubpytorchMIT report
ZephyrZhuQi/ssbaseline mentioned on GitHubpytorchNOASSERTION report
allenai/pythia mentioned on GitHubpytorchNOASSERTION report
facebookresearch/mmf mentioned on GitHubpytorchNOASSERTION report
facebookresearch/pythia mentioned on GitHubpytorchNOASSERTION report
jackroos/pythia mentioned on GitHubpytorchNOASSERTION report
ronghanghu/pythia mentioned on GitHubpytorchNOASSERTION report

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.

Code Syntology ran Syntology

13 samples harvested; 4 ran; 1 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · violated contract
9unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

answer_filter jnhwkim/ban-vqa/dataset.py official repository ran · violated contract MIT (permissive) · cf2efa825f4afaf0 · report
is_howmany jnhwkim/ban-vqa/dataset.py official repository ran · violated contract MIT (permissive) · ac9f54e37ab206e4 · report
pil_loader jnhwkim/ban-vqa/utils.py official repository ran · honoured contract MIT (permissive) · 1df9a5ffd9b38c34 · report
compute_recall_with_logits jnhwkim/ban-vqa/train_flickr.py official repository unverified MIT (permissive) · 5a8370941ac95d70 · report
evaluate jnhwkim/ban-vqa/train_flickr.py official repository unverified MIT (permissive) · 728c76c97b1bb97a · report
load_folder jnhwkim/ban-vqa/utils.py official repository unverified MIT (permissive) · 8c1252eacab71602 · report
load_imageid jnhwkim/ban-vqa/utils.py official repository unverified MIT (permissive) · bf90bd27fe08f3a2 · report
tile_2d_over_nd Cyanogenoid/vqa-counting/vqa-v2/model.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · b3299f7858d7d2f2 · report
apply_attention Cyanogenoid/vqa-counting/vqa-v2/model.py community (archive-listed) unverified MIT (permissive) · 26e02979502211f1 · report
batch_accuracy Cyanogenoid/vqa-counting/vqa-v2/utils.py community (archive-listed) unverified MIT (permissive) · 2c844ba6b5d8ece2 · report
collate_fn Cyanogenoid/vqa-counting/vqa-v2/data.py community (archive-listed) unverified MIT (permissive) · 28e89c10480659aa · report
extract_vocab Cyanogenoid/vqa-counting/vqa-v2/preprocess-vocab.py community (archive-listed) unverified MIT (permissive) · 8e41785566e403d2 · report
prepare_answers Cyanogenoid/vqa-counting/vqa-v2/data.py community (archive-listed) unverified MIT (permissive) · 1e3e251c3f07251d · report

Tasks

Visual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Phrase Grounding Flickr30k Entities Test BAN (Bottom-Up detector) R@1 69.69 #11 of 18 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test BAN (Bottom-Up detector) R@10 86.35 #11 of 18 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test BAN (Bottom-Up detector) R@5 84.22 #11 of 18 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-dev BAN+Glove+Counter Accuracy 70.04 #31 of 56 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std BAN+Glove+Counter overall 70.4 #27 of 38 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