Papers › Vision-Language Pre-Training with Triple Contrastive Learning

Vision-Language Pre-Training with Triple Contrastive Learning

21 Feb 2022CVPR 2022 1arXiv:2202.10401archive 2025-07-28

Jinyu Yang, Jiali Duan, Son Tran, Yi Xu, Sampath Chanda, Liqun Chen, Belinda Zeng, Trishul Chilimbi, Junzhou Huang

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information (MI) between an image and its matched text. However, simply performing cross-modal alignment (CMA) ignores data potential within each modality, which may result in degraded representations. For instance, although CMA-based models are able to map image-text pairs close together in the embedding space, they fail to ensure that similar inputs from the same modality stay close by. This problem can get even worse when the pre-training data is noisy. In this paper, we propose triple contrastive learning (TCL) for vision-language pre-training by leveraging both cross-modal and intra-modal self-supervision. Besides CMA, TCL introduces an intra-modal contrastive objective to provide complementary benefits in representation learning. To take advantage of localized and structural information from image and text input, TCL further maximizes the average MI between local regions of image/text and their global summary. To the best of our knowledge, ours is the first work that takes into account local structure information for multi-modality representation learning. Experimental evaluations show that our approach is competitive and achieves the new state of the art on various common down-stream vision-language tasks such as image-text retrieval and visual question answering.

PaperPDFConference PDFCodeCode Syntology ran

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 2 code samples harvested from 1 repository linked to this paper: 1 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; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 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 date is recorded for the sample that ran: its level was written before Syntology's graph kept the date.

uta-smile/TCL officialmentioned in papermentioned on GitHubpytorchMITSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified 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

2 samples harvested: 1 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; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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; the contract check could not run
1unverified

Licence: 0 of the 2 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 uta-smile/TCL. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

uta-smile/TCL official repository 2 samples, 1 ran (1 instrument-failed) · 1 unverified
itm_eval in 27 papers Retrieval.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · c7f85279d772ea19 · report fixture: signature scores_i2t:ndarray/2/float, scores_t2i:ndarray/2/float, txt2img:dict/0/?, img2txt:dict/0/? · returned dict · level recorded, date not recorded

Tasks

Contrastive LearningCross-Modal RetrievalImage-text RetrievalQuestion AnsweringRepresentation LearningRetrievalText RetrievalVisual Question AnsweringVisual Question Answering (VQA)Zero-Shot Cross-Modal Retrievalcross-modal alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval COCO 2014 TCL Image-to-text R@1 75.6 #18 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 TCL Image-to-text R@10 96.7 #18 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 TCL Image-to-text R@5 92.8 #18 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 TCL Text-to-image R@1 59.0 #18 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 TCL Text-to-image R@10 89.9 #18 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 TCL Text-to-image R@5 83.2 #18 of 36 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 TCL Image-to-text R@1 71.4 #3 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 TCL Image-to-text R@10 95.4 #3 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 TCL Image-to-text R@5 90.8 #3 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 TCL Text-to-image R@1 53.5 #3 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 TCL Text-to-image R@10 87.1 #3 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 TCL Text-to-image R@5 79.0 #3 of 18 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

Contrastive LearningInfoNCE

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