Papers › CLIPArTT: Adaptation of CLIP to New Domains at Test Time

CLIPArTT: Adaptation of CLIP to New Domains at Test Time

1 May 2024arXiv:2405.00754archive 2025-07-28

Gustavo Adolfo Vargas Hakim, David Osowiechi, Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, their performance diminishes in the presence of domain shifts. In this study, we introduce CLIP Adaptation duRing Test-Time (CLIPArTT), a fully test-time adaptation (TTA) approach for CLIP, which involves automatic text prompts construction during inference for their use as text supervision. Our method employs a unique, minimally invasive text prompt tuning process, wherein multiple predicted classes are aggregated into a single new text prompt, used as \emph{pseudo label} to re-classify inputs in a transductive manner. Additionally, we pioneer the standardization of TTA benchmarks (e.g., TENT) in the realm of VLMs. Our findings demonstrate that, without requiring additional transformations nor new trainable modules, CLIPArTT enhances performance dynamically across non-corrupted datasets such as CIFAR-100, corrupted datasets like CIFAR-100-C and ImageNet-C, alongside synthetic datasets such as VisDA-C. This research underscores the potential for improving VLMs' adaptability through novel test-time strategies, offering insights for robust performance across varied datasets and environments. The code can be found at: https://github.com/dosowiechi/CLIPArTT.git

PaperPDFCodeCode 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="2405.00754")

Code

Syntology Ran 11 of 15 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 2 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dosowiechi/clipartt officialmentioned in papermentioned 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

15 samples harvested; 11 ran; 0 honoured the contract we drafted; 4 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
2ran · fixture could not drive it
6ran
4unverified

Licence: 15 of the 15 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 dosowiechi/clipartt. “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.

accuracy dosowiechi/clipartt/utils/utils.py official repository ran · fixture could not drive it no licence file found · pointer only · b0f936d4d6ae3b8c · report
basic_clean dosowiechi/clipartt/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 98f385d847636a3e · report
cross_entropy dosowiechi/clipartt/models/tent.py official repository ran fingerprinted no licence file found · pointer only · d858deb1b3a2d3ba · report
entropy_energy dosowiechi/clipartt/models/lame.py official repository ran fingerprinted no licence file found · pointer only · 473a24407468b75e · report
get_pairs dosowiechi/clipartt/clip/simple_tokenizer.py official repository ran · our draft was wrong no licence file found · pointer only · d919ae32e5e4e616 · report
getprompt dosowiechi/clipartt/models/tent.py official repository ran no licence file found · pointer only · e7236889a0d75f77 · report
prepare_val_data dosowiechi/clipartt/utils/prepare_dataset.py official repository ran no licence file found · pointer only · cc8f4613f74df21b · report
setup_optimizer dosowiechi/clipartt/adapt.py official repository ran no licence file found · pointer only · b3a7110b4cd7c335 · report
softmax_entropy dosowiechi/clipartt/models/tent.py official repository ran · fixture could not drive it no licence file found · pointer only · 3078648c75e3e1e3 · report
test_batch dosowiechi/clipartt/utils/utils.py official repository ran no licence file found · pointer only · 077971bc206bae40 · report
whitespace_clean dosowiechi/clipartt/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 9542161e9640b858 · report
adapt_batch dosowiechi/clipartt/utils/utils.py official repository unverified no licence file found · pointer only · ad2900d99122fdff · report
build_model dosowiechi/clipartt/clip/model.py official repository unverified no licence file found · pointer only · 38c09396452c23a0 · report
laplacian_optimization dosowiechi/clipartt/models/lame.py official repository unverified no licence file found · pointer only · d2597d43cbd2fbca · report
load dosowiechi/clipartt/clip/clip.py official repository unverified no licence file found · pointer only · 2da7ec0975be872a · report

Tasks

Pseudo LabelTest-time AdaptationZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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