Papers › ALIP: Adaptive Language-Image Pre-training with Synthetic Caption

ALIP: Adaptive Language-Image Pre-training with Synthetic Caption

16 Aug 2023ICCV 2023 1arXiv:2308.08428archive 2025-07-28

Kaicheng Yang, Jiankang Deng, Xiang An, Jiawei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. To address this issue, we first utilize the OFA model to generate synthetic captions that focus on the image content. The generated captions contain complementary information that is beneficial for pre-training. Then, we propose an Adaptive Language-Image Pre-training (ALIP), a bi-path model that integrates supervision from both raw text and synthetic caption. As the core components of ALIP, the Language Consistency Gate (LCG) and Description Consistency Gate (DCG) dynamically adjust the weights of samples and image-text/caption pairs during the training process. Meanwhile, the adaptive contrastive loss can effectively reduce the impact of noise data and enhances the efficiency of pre-training data. We validate ALIP with experiments on different scales of models and pre-training datasets. Experiments results show that ALIP achieves state-of-the-art performance on multiple downstream tasks including zero-shot image-text retrieval and linear probe. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/ALIP.

PaperPDFConference PDFCodeCode 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 10 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 5 ran (4 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.

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

deepglint/alip officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 5 ran (1 instrument-failed) · 5 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

10 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 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
4ran
5unverified

Licence: 10 of the 10 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 deepglint/alip. “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.

deepglint/alip official repository 10 samples, 5 ran (1 instrument-failed) · 5 unverified
Bottleneck in 98 papers src/open_alip/model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · c633512829e5fe31 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
src/open_alip/model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 68409bf9a33a762c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ResidualAttentionBlock in 38 papers src/open_alip/model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 84ad28ccef1c7735 · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
Transformer in 173 papers src/open_alip/model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · e7861f77ffcac38a · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
freeze_batch_norm_2d in 15 papers src/open_alip/model.py ran · our draft was wrong no licence file found · pointer only · bbc121b32c8ac8ec · report fixture: signature module:callable/0/?, module_match:dict/0/?, name:str/0/str · returned SimpleModel · level recorded 2026-09-22
ALIP src/open_alip/model.py unverified no licence file found · pointer only · afaff1a400a3d3f0 · report
ALIPTextCfg src/open_alip/model.py unverified no licence file found · pointer only · bcc5f816fd3d9665 · report
ALIPVisionCfg src/open_alip/model.py unverified no licence file found · pointer only · 83728ce18d451bd0 · report
ModifiedResNet in 15 papers src/open_alip/model.py unverified no licence file found · pointer only · 1bb95acac49af730 · report
VisualTransformer in 12 papers src/open_alip/model.py unverified no licence file found · pointer only · 4a20fae4815b1a33 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for ALIP (graph method: ALIP). 13 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. ALIP entry · level 0 · unverified · afaff1a400a3d3f0
  2. ALIPTextCfg model · level 0 · unverified · bcc5f816fd3d9665
  3. ALIPVisionCfg model · level 0 · unverified · 83728ce18d451bd0
  4. LayerNorm helper · level 1 · ran · 68409bf9a33a762c
  5. ModifiedResNet model · level 0 · unverified · 1bb95acac49af730
  6. QuickGELU helper · level 1 · ran · 8c5c4de012c0aab9
  7. Transformer model · level 1 · ran · e7861f77ffcac38a
  8. VisualTransformer model · level 0 · unverified · 4a20fae4815b1a33
  9. AttentionPool2d helper · level 1 · ran · 1371958d4e89f57a
  10. Bottleneck helper · level 1 · ran · c633512829e5fe31
  11. freeze_batch_norm_2d helper · level 1 · ran · our draft was wrong · bbc121b32c8ac8ec
  12. ResidualAttentionBlock model · level 1 · ran · 84ad28ccef1c7735
  13. _ntuple helper · level 1 · ran · our draft was wrong · 553ee0765abad219

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="2308.08428") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action ClassificationImage-text RetrievalRepresentation LearningRetrievalText Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-700-2020 ALIP-ViT B/32 LAION30M Top 1 Accuracy 50.6 #1 of 3 Archive leaderboard report
Action Classification Kinetics-700-2020 ALIP-ViT B/16 LAION10M Top 1 Accuracy 50.1 #2 of 3 Archive leaderboard report
Action Classification Kinetics-700-2020 ALIP-ViT B/32 LAION10M Top 1 Accuracy 46.4 #3 of 3 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

FocusOFA

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