Papers › Conditional Prompt Learning for Vision-Language Models

Conditional Prompt Learning for Vision-Language Models

10 Mar 2022CVPR 2022 1arXiv:2203.05557archive 2025-07-28

Kaiyang Zhou, Jingkang Yang, Chen Change Loy, Ziwei Liu

With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed method named Context Optimization (CoOp) introduces the concept of prompt learning -- a recent trend in NLP -- to the vision domain for adapting pre-trained vision-language models. Specifically, CoOp turns context words in a prompt into a set of learnable vectors and, with only a few labeled images for learning, can achieve huge improvements over intensively-tuned manual prompts. In our study we identify a critical problem of CoOp: the learned context is not generalizable to wider unseen classes within the same dataset, suggesting that CoOp overfits base classes observed during training. To address the problem, we propose Conditional Context Optimization (CoCoOp), which extends CoOp by further learning a lightweight neural network to generate for each image an input-conditional token (vector). Compared to CoOp's static prompts, our dynamic prompts adapt to each instance and are thus less sensitive to class shift. Extensive experiments show that CoCoOp generalizes much better than CoOp to unseen classes, even showing promising transferability beyond a single dataset; and yields stronger domain generalization performance as well. Code is available at https://github.com/KaiyangZhou/CoOp.

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

No sample from the archive's official repository (kaiyangzhou/coop) is linked to this paper; the 6 samples below come from 1 community repository. Syntology harvested code from kaiyangzhou/coop for another paper.

kaiyangzhou/coop: Syntology's graph links these samples to Visual-Language Prompt Tuning with Knowledge-guided Context Optimization (arXiv:2303.13283; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.

Syntology 6 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: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 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.

No sample is linked to this paper from 10 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

kaiyangzhou/coop officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Visual-Language Prompt Tuning with Knowledge-guided Context Optimization (arXiv:2303.13283; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Gahyeonkim09/AAPL mentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (3 instrument-failed) · 2 unverified report
ThomasWangY/2024-AAAI-HPT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Prompt for Vision-Language Models (arXiv:2109.01134; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
Vill-Lab/2024-TIP-MetaPrompt mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Prompt for Vision-Language Models (arXiv:2109.01134; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
azshue/TPT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models (arXiv:2209.07511; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
healthx-lab/biomedcoop mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CVF open access id Koleilat_BiomedCoOp_Learning_to_Prompt_for_Biomedical_Vision-Language_Models_CVPR_2025_paper (that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
hhenryd/tap mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Prompt for Vision-Language Models (arXiv:2109.01134; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
kaiyangzhou/on-device-dg mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
muzairkhattak/multimodal-prompt-learning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MaPLe: Multi-modal Prompt Learning (arXiv:2210.03117; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
muzairkhattak/protext mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Prompt with Text Only Supervision for Vision-Language Models (arXiv:2401.02418; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
saic-fi/bayesian-prompt-learning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Bayesian Prompt Learning for Image-Language Model Generalization (arXiv:2210.02390; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
vill-lab/2024-aaai-hpt mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models (arXiv:2312.06323; that paper's own run record: 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) and AAAI id aaai_28387 (that paper's own run record: 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); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

6 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
2unverified

Licence: 3 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 Gahyeonkim09/AAPL. “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.

Gahyeonkim09/AAPL community (archive-listed) 6 samples, 4 ran (3 instrument-failed) · 2 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
compute_ci95 in 38 papers parse_test_res.py ran · honoured contract fingerprinted MIT (permissive) · ba26afd892405335 · report fixture: signature res:ndarray/1/float · returned float64 · level recorded 2026-09-24
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.py unverified MIT (permissive) here; the stored copy is pointer only · c47aa9e5b049a11d · report
load in 392 papers clip/clip.py unverified MIT (permissive) · fbf8c0143d9c48e3 · report

Tasks

Domain GeneralizationPrompt EngineeringPrompt Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Prompt Engineering Caltech-101 CoCoOp Harmonic mean 95.84 #13 of 14 Archive leaderboard report
Prompt Engineering DTD CoCoOp Harmonic mean 64.85 #13 of 14 Archive leaderboard report
Prompt Engineering EuroSAT CoCoOp Harmonic mean 71.21 #13 of 14 Archive leaderboard report
Prompt Engineering FGVC-Aircraft CoCoOp Harmonic mean 27.74 #14 of 14 Archive leaderboard report
Prompt Engineering Food-101 CoCoOp Harmonic mean 90.99 #12 of 13 Archive leaderboard report
Prompt Engineering ImageNet CoCoOp Harmonic mean 73.10 #14 of 15 Archive leaderboard report
Prompt Engineering ImageNet V2 CoCoOp Top-1 accuracy % 64.07 #6 of 8 Archive leaderboard report
Prompt Engineering ImageNet-A CoCoOp Top-1 accuracy % 50.63 #7 of 9 Archive leaderboard report
Prompt Engineering ImageNet-R CoCoOP Top-1 accuracy % 76.18 #8 of 9 Archive leaderboard report
Prompt Engineering ImageNet-S CoCoOp Top-1 accuracy % 48.75 #8 of 9 Archive leaderboard report
Prompt Engineering Oxford 102 Flower CoCoOp Harmonic mean 81.71 #13 of 14 Archive leaderboard report
Prompt Engineering Oxford-IIIT Pet Dataset CoCoOp Harmonic mean 96.43 #9 of 14 Archive leaderboard report
Prompt Engineering SUN397 CoCoOp Harmonic mean 78.27 #13 of 14 Archive leaderboard report
Prompt Engineering Stanford Cars CoCoOp Harmonic mean 72.01 #13 of 14 Archive leaderboard report
Prompt Engineering UCF101 CoCoOp Harmonic mean 77.64 #13 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.

Methods

BASECLIPCoOp

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