Papers › VisualBERT: A Simple and Performant Baseline for Vision and Language

VisualBERT: A Simple and Performant Baseline for Vision and Language

9 Aug 2019arXiv:1908.03557archive 2025-07-28

Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang

We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly align elements of an input text and regions in an associated input image with self-attention. We further propose two visually-grounded language model objectives for pre-training VisualBERT on image caption data. Experiments on four vision-and-language tasks including VQA, VCR, NLVR2, and Flickr30K show that VisualBERT outperforms or rivals with state-of-the-art models while being significantly simpler. Further analysis demonstrates that VisualBERT can ground elements of language to image regions without any explicit supervision and is even sensitive to syntactic relationships, tracking, for example, associations between verbs and image regions corresponding to their arguments.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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):

Code

Syntology 9 code samples harvested from 3 repositories linked to this paper: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 3 repositories, 4 ran (2 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

chenkangyang/paddle_visual_bert mentioned on GitHubpaddleSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
gchhablani/multilingual-vqa mentioned on GitHubjaxSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
lalithjets/surgical_vqa mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer (arXiv:2206.11053; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
longbai1006/surgical-vqla mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question... (arXiv:2305.11692; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
social-ai-studio/matk mentioned on GitHubpytorchSyntology: not harvested report
uclanlp/visualbert mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions (arXiv:2010.12831; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-1 mindsporeSyntology: not harvested report
MindCode-4/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViTamin: Designing Scalable Vision Models in the Vision-Language Era (arXiv:2404.02132; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
YIKUAN8/Transformers-VQA pytorchSyntology: 3 samples, 0 ran · 3 unverified report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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.

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

9 samples harvested: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
1ran; the contract check could not run
2ran
5unverified

Licence: 6 of the 9 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

chenkangyang/paddle_visual_bert community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
perform_truncate run_pretrain.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · cd39cffdc7b1f9c3 · report fixture: signature max_seq_length:int/0/int, text_a:list/1/int, text_b:list/1/int · returned tuple · level recorded 2026-09-24
random_word in 5 papers run_pretrain.py ran · our draft was wrong no licence file found · pointer only · 1d3d00a8a5932be0 · report fixture: signature tokens:list/1/str, tokenizer:MinimalTokenizer/0/?, probability:float/0/float · returned tuple · level recorded 2026-09-22
prepare_train_features_single run_pretrain.py unverified no licence file found · pointer only · 49436f86e6503e90 · report
gchhablani/multilingual-vqa community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
CLIPVisionBertConfig models/flax_clip_vision_bert/modeling_clip_vision_bert.py ran MIT (permissive) · 74b2fcf39fdad75a · report fixture: returned CLIPVisionBertConfig · level recorded 2026-09-22
FlaxCLIPVisionBertModule models/flax_clip_vision_bert/modeling_clip_vision_bert.py ran MIT (permissive) · eed1fcab3a96812d · report fixture: returned FlaxCLIPVisionBertModule · level recorded 2026-09-22
FlaxCLIPVisionBertEmbeddings models/flax_clip_vision_bert/modeling_clip_vision_bert.py unverified MIT (permissive) · bc82bcf6d781550f · report
YIKUAN8/Transformers-VQA community (archive-listed) 3 samples, 0 ran · 3 unverified
BertEncoder in 20 papers src/modeling.py unverified no licence file found · pointer only · 59f36be33253afad · report
VBBertModel src/modeling.py unverified no licence file found · pointer only · 2e705a7d909038d1 · report
VisualBertEmbeddings src/modeling.py unverified no licence file found · pointer only · 7c7933295057c6b3 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for VisualBERT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for VisualBERT (graph method: VisualBERT). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. FlaxCLIPVisionBertModule entry · level 1 · ran · eed1fcab3a96812d
  2. CLIPVisionBertConfig helper · level 1 · ran · 74b2fcf39fdad75a
  3. FlaxCLIPVisionBertEmbeddings model · level 0 · unverified · bc82bcf6d781550f

harvested Assembly for VisualBERT (graph method: VisualBERT). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. prepare_train_features_single entry · level 0 · unverified · 49436f86e6503e90
  2. perform_truncate helper · level 1 · ran; the contract check could not run (RAISES) · cd39cffdc7b1f9c3
  3. random_word helper · level 1 · ran · our draft was wrong · 1d3d00a8a5932be0

harvested Assembly for VisualBERT (graph method: VisualBERT). 24 bricks; individually on a fixture: 12 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. VBBertModel entry · level 0 · unverified · 2e705a7d909038d1
  2. BertEncoder model · level 0 · unverified · 59f36be33253afad
  3. BertPooler model · level 1 · ran · 8f1a0b9437ccc562
  4. BertPreTrainedModel helper · level 0 · unverified · 805f9fc004ffa11b
  5. VisualBertEmbeddings model · level 0 · unverified · 7c7933295057c6b3
  6. BertLayer helper · level 0 · unverified · 2f7d2c26e185cb3f
  7. BertConfig helper · level 1 · ran · 5324d31f8ea9ca59
  8. cached_path helper · level 0 · unverified · a4e8483353cec520
  9. load_tf_weights_in_bert helper · level 0 · unverified · 7099305544368003
  10. BertIntermediate helper · level 1 · ran · c7123d4962da3767
  11. BertOutput helper · level 1 · ran · 61f383a856ac089e
  12. BertSelfattLayer helper · level 1 · ran · 9c6012122feb6f81
  13. get_from_cache helper · level 0 · unverified · 242c3c3d7e930e18
  14. BertAttOutput helper · level 1 · ran · 5ccefc0113e7b26e
  15. BertAttention helper · level 1 · ran · b8c495ff176f844a
  16. http_get helper · level 0 · unverified · 18f49ada16168f38
  17. s3_etag helper · level 0 · unverified · 51dd06ec77c8a8d1
  18. s3_get helper · level 0 · unverified · 1079045e75efbf23
  19. url_to_filename helper · level 1 · ran · our draft was wrong · 5eff22fa0a651276
  20. s3_request helper · level 1 · ran · our draft was wrong · 7661139be003d514
  21. split_s3_path helper · level 0 · unverified · d3852f416bfe86c3
  22. VisualConfig helper · level 1 · ran · 3644fb46790a5387
  23. gelu helper · level 1 · ran · honoured contract · fdc64f4c72036ae4
  24. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1908.03557") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingVisual Question Answering (VQA)Visual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Phrase Grounding Flickr30k Entities Dev VisualBERT R@1 70.4 #3 of 3 Archive leaderboard report
Phrase Grounding Flickr30k Entities Dev VisualBERT R@10 86.31 #3 of 3 Archive leaderboard report
Phrase Grounding Flickr30k Entities Dev VisualBERT R@5 84.49 #3 of 3 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test VisualBERT R@1 71.33 #10 of 18 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test VisualBERT R@10 86.51 #10 of 18 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test VisualBERT R@5 84.98 #10 of 18 Archive leaderboard report
Visual Question Answering (VQA) VCR (Q-A) dev VisualBERT Accuracy 70.8 #3 of 3 Archive leaderboard report
Visual Question Answering (VQA) VCR (Q-A) test VisualBERT Accuracy 71.6 #9 of 11 Archive leaderboard report
Visual Question Answering (VQA) VCR (Q-AR) dev VisualBERT Accuracy 52.2 #3 of 3 Archive leaderboard report
Visual Question Answering (VQA) VCR (Q-AR) test VisualBERT Accuracy 52.4 #7 of 7 Archive leaderboard report
Visual Question Answering (VQA) VCR (QA-R) dev VisualBERT Accuracy 73.2 #3 of 3 Archive leaderboard report
Visual Question Answering (VQA) VCR (QA-R) test VisualBERT Accuracy 73.2 #8 of 8 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-dev VisualBERT Accuracy 70.8 #28 of 56 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std VisualBERT overall 71 #24 of 38 Archive leaderboard report
Visual Reasoning NLVR VisualBERT Accuracy (Dev) 67.4% #1 of 1 Archive leaderboard report
Visual Reasoning NLVR VisualBERT Accuracy (Test-P) 67% #1 of 1 Archive leaderboard report
Visual Reasoning NLVR VisualBERT Accuracy (Test-U) 67.3% #1 of 1 Archive leaderboard report
Visual Reasoning NLVR2 Dev VisualBERT Accuracy 66.7 #15 of 15 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.

Methods

Introduced by this paper: VisualBERT

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerVisualBERT

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