Papers › UNITER: UNiversal Image-TExt Representation Learning

UNITER: UNiversal Image-TExt Representation Learning

25 Sep 2019ECCV 2020 8arXiv:1909.11740archive 2025-07-28

Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu

Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. We design four pre-training tasks: Masked Language Modeling (MLM), Masked Region Modeling (MRM, with three variants), Image-Text Matching (ITM), and Word-Region Alignment (WRA). Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i.e., masked language/region modeling is conditioned on full observation of image/text). In addition to ITM for global image-text alignment, we also propose WRA via the use of Optimal Transport (OT) to explicitly encourage fine-grained alignment between words and image regions during pre-training. Comprehensive analysis shows that both conditional masking and OT-based WRA contribute to better pre-training. We also conduct a thorough ablation study to find an optimal combination of pre-training tasks. Extensive experiments show that UNITER achieves new state of the art across six V+L tasks (over nine datasets), including Visual Question Answering, Image-Text Retrieval, Referring Expression Comprehension, Visual Commonsense Reasoning, Visual Entailment, and NLVR². Code is available at https://github.com/ChenRocks/UNITER.

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="1909.11740")

Code

Syntology Ran 3 of 3 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: community (archive-listed): 3 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ChenRocks/UNITER officialmentioned in papermentioned on GitHubpytorch report
SDLZY/VCR_Align mentioned on GitHubpytorch report
lichengunc/pretrain-vl-data mentioned on GitHubMIT report
necla-ml/SNLI-VE mentioned on GitHubBSD-3-Clause report
vladsandulescu/hatefulmemes mentioned on GitHubpytorch report
xiaomin418/cfsum mentioned on GitHubpytorch 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

3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 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.

3ran · our draft was wrong

Licence: 2 of the 3 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.

evaluate SDLZY/VCR_Align/inf_nlvr2.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 347953d8bd5d46e8 · report
merge_sub_word xiaomin418/cfsum/src/inference.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 32ec2df257af200f · report
merge_sub_word2score xiaomin418/cfsum/src/inference.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 9bd01ccf1581d378 · report

Tasks

Image-text RetrievalImage-text matchingLanguage ModelingLanguage ModellingMasked Language ModelingQuestion AnsweringReferring ExpressionReferring Expression ComprehensionRepresentation LearningRetrievalText MatchingText RetrievalVisual Commonsense ReasoningVisual EntailmentVisual Question AnsweringVisual Question Answering (VQA)Visual ReasoningZero-Shot Cross-Modal Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Entailment SNLI-VE test UNITER (Large) Accuracy 78.98 #7 of 8 Archive leaderboard report
Visual Entailment SNLI-VE val UNITER Accuracy 78.98 #8 of 9 Archive leaderboard report
Visual Question Answering (VQA) VCR (Q-A) test UNITER-large (10 ensemble) Accuracy 79.8 #3 of 11 Archive leaderboard report
Visual Question Answering (VQA) VCR (Q-A) test UNITER (Large) Accuracy 77.3 #5 of 11 Archive leaderboard report
Visual Question Answering (VQA) VCR (Q-AR) test UNITER (Large) Accuracy 62.8 #3 of 7 Archive leaderboard report
Visual Question Answering (VQA) VCR (QA-R) test UNITER-large (ensemble of 10 models) Accuracy 83.4 #3 of 8 Archive leaderboard report
Visual Question Answering (VQA) VCR (QA-R) test UNITER (Large) Accuracy 80.8 #4 of 8 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-dev UNITER (Large) Accuracy 73.24 #21 of 56 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std UNITER (Large) overall 73.4 #19 of 38 Archive leaderboard report
Visual Reasoning NLVR2 Test UNITER (Large) Accuracy 79.5 #11 of 14 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k UNITER Image-to-text R@1 80.7 #18 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k UNITER Image-to-text R@10 98.0 #18 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k UNITER Image-to-text R@5 95.7 #18 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k UNITER Text-to-image R@1 66.2 #18 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k UNITER Text-to-image R@10 92.9 #18 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k UNITER Text-to-image R@5 88.4 #18 of 22 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: UNITER

UNITER

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