Papers › Consistency-guided Prompt Learning for Vision-Language Models

Consistency-guided Prompt Learning for Vision-Language Models

1 Jun 2023arXiv:2306.01195archive 2025-07-28

Shuvendu Roy, Ali Etemad

We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting. The basic idea of CoPrompt is to enforce a consistency constraint in the prediction of the trainable and pre-trained models to prevent overfitting on the downstream task. Additionally, we introduce the following two components into our consistency constraint to further boost the performance: enforcing consistency on two perturbed inputs and combining two dominant paradigms of tuning, prompting and adapter. Enforcing consistency on perturbed input serves to further regularize the consistency constraint, thereby improving generalization. Moreover, the integration of adapters and prompts not only enhances performance on downstream tasks but also offers increased tuning flexibility in both input and output spaces. This facilitates more effective adaptation to downstream tasks in a few-shot learning setting. Experiments show that CoPrompt outperforms existing methods on a range of evaluation suites, including base-to-novel generalization, domain generalization, and cross-dataset evaluation. On generalization, CoPrompt improves the state-of-the-art on zero-shot tasks and the overall harmonic mean over 11 datasets. Detailed ablation studies show the effectiveness of each of the components in CoPrompt. We make our code available at https://github.com/ShuvenduRoy/CoPrompt.

PaperPDFCodeCode 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 7 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 4 ran (1 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

shuvenduroy/coprompt officialmentioned in papermentioned on GitHubpytorchMITSyntology: 7 samples, 4 ran (3 instrument-failed) · 3 unverified report
ShuvenduRoy/FER_TL_PipelineTraining mentioned on GitHubSyntology: not harvested 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

7 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 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.

3ran · our draft was wrong
1ran
3unverified

Licence: 4 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from shuvenduroy/coprompt. “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.

shuvenduroy/coprompt official repository 7 samples, 4 ran (3 instrument-failed) · 3 unverified
basic_clean in 217 papers clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
cosine_loss in 10 papers trainers/coprompt.py ran fingerprinted MIT (permissive) · b45d4ac2bba7e906 · report fixture: signature student_embedding:Tensor/2/float, teacher_embedding:Tensor/2/float · returned Tensor · level recorded 2026-09-26
get_pairs in 260 papers clip/simple_tokenizer.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
whitespace_clean in 230 papers clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
build_model in 469 papers clip/model_clip_original.py unverified MIT (permissive) here; the stored copy is pointer only · c47aa9e5b049a11d · report
build_model in 469 papers clip/model.py unverified MIT (permissive) here; the stored copy is pointer only · 918dfac560aed1c9 · report
load in 392 papers clip/clip.py unverified MIT (permissive) · fbf8c0143d9c48e3 · report

Tasks

Domain GeneralizationFew-Shot LearningPrompt EngineeringPrompt Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Prompt Engineering Caltech-101 CoPrompt Harmonic mean 96.55 #6 of 14 Archive leaderboard report
Prompt Engineering DTD CoPrompt Harmonic mean 72.79 #5 of 14 Archive leaderboard report
Prompt Engineering EuroSAT CoPrompt Harmonic mean 85.84 #5 of 14 Archive leaderboard report
Prompt Engineering FGVC-Aircraft CoPrompt Harmonic mean 39.76 #9 of 14 Archive leaderboard report
Prompt Engineering Food-101 CoPrompt Harmonic mean 91.40 #2 of 13 Archive leaderboard report
Prompt Engineering ImageNet CoPrompt Harmonic mean 74.33 #5 of 15 Archive leaderboard report
Prompt Engineering ImageNet-A CoPrompt Top-1 accuracy % 50.50 #8 of 9 Archive leaderboard report
Prompt Engineering ImageNet-R CoPrompt Top-1 accuracy % 77.51 #5 of 9 Archive leaderboard report
Prompt Engineering ImageNet-S CoPrompt Top-1 accuracy % 49.43 #3 of 9 Archive leaderboard report
Prompt Engineering Oxford 102 Flower CoPrompt Harmonic mean 85.71 #9 of 14 Archive leaderboard report
Prompt Engineering Oxford-IIIT Pet Dataset CoPrompt Harmonic mean 96.87 #3 of 14 Archive leaderboard report
Prompt Engineering SUN397 CoPrompt Harmonic mean 81.31 #2 of 14 Archive leaderboard report
Prompt Engineering Stanford Cars CoPrompt Harmonic mean 75.66 #7 of 14 Archive leaderboard report
Prompt Engineering UCF101 CoPrompt Harmonic mean 83.07 #7 of 14 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