Papers › Large-Scale Adversarial Training for Vision-and-Language Representation Learning

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

11 Jun 2020NeurIPS 2020 12arXiv:2006.06195archive 2025-07-28

Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, Jingjing Liu

We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning. Instead of adding adversarial perturbations on image pixels and textual tokens, we propose to perform adversarial training in the embedding space of each modality. To enable large-scale training, we adopt the "free" adversarial training strategy, and combine it with KL-divergence-based regularization to promote higher invariance in the embedding space. We apply VILLA to current best-performing V+L models, and achieve new state of the art on a wide range of tasks, including Visual Question Answering, Visual Commonsense Reasoning, Image-Text Retrieval, Referring Expression Comprehension, Visual Entailment, and NLVR2.

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="2006.06195")

Code

Syntology Ran 10 of 20 code samples harvested from 2 repositories linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 20 samples from 2 repositories, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhegan27/LXMERT-AdvTrain officialmentioned in papermentioned on GitHubpytorch report
zhegan27/VILLA officialmentioned in papermentioned on GitHubpytorchMIT 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

20 samples harvested; 10 ran; 1 honoured the contract we drafted; 10 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
2ran · our draft was wrong
1ran · fixture could not drive it
6ran
10unverified

Licence: 6 of the 20 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.

swish zhegan27/VILLA/model/layer.py official repository ran · our draft was wrong fingerprinted MIT recorded; this copy not marked cleared · pointer only · 0f786c407fb1ee4c · report
BertEmbeddings zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository ran MIT (permissive) · 7cd6bab68e15976d · report
BertPredictionHeadTransform zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2ba3b1dfb07ba4b1 · report
BertVisualAnswerHead zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2c8c022f71d9ae6e · report
BertVisualObjHead zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 0e7be2781b71b508 · report
GeLU zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · ce655ad320784ce8 · report
VisualFeatEncoder zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 1bea2e32e2dc619d · report
cost_matrix_cosine zhegan27/VILLA/model/ot.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 9c9d2823696faa43 · report
gelu zhegan27/VILLA/model/layer.py official repository ran · honoured contract fingerprinted MIT recorded; this copy not marked cleared · pointer only · fdc64f4c72036ae4 · report
multi_head_attention_forward zhegan27/VILLA/model/attention.py official repository ran · our draft was wrong MIT (permissive) · fed42c63be2ceb6c · report
BertLMPredictionHead zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository unverified MIT (permissive) · 77ff902ef6858211 · report
BertPreTrainingHeads zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository unverified MIT (permissive) · 781e8b75f1ca0f7c · report
LXRTEncoder zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository unverified MIT (permissive) · 2c0fd477bfbddac7 · report
LXRTModel zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository unverified MIT (permissive) · 95e61302335909fb · report
LXRTPretraining zhegan27/LXMERT-AdvTrain/src/lxrt/modeling.py official repository unverified MIT (permissive) · 6f76d36162ffef27 · report
compute_score_with_logits zhegan27/VILLA/inf_vqa.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 2731fd9de6d31bc0 · report
evaluate zhegan27/VILLA/inf_nlvr2.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 28e194bd5c984ae7 · report
ipot zhegan27/VILLA/model/ot.py official repository unverified MIT (permissive) · cbf43203110456f0 · report
save_for_submission zhegan27/VILLA/inf_vcr.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 70361102cdeaaf85 · report
trace zhegan27/VILLA/model/ot.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · d3f4c62a97861b9d · report

Tasks

Image-text RetrievalQuestion AnsweringReferring ExpressionReferring Expression ComprehensionRepresentation LearningRetrievalText RetrievalVisual Commonsense ReasoningVisual EntailmentVisual Question AnsweringVisual Question Answering (VQA)Visual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Entailment SNLI-VE val VILLA-LARGE Accuracy 80.18 #7 of 9 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