Papers › OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation

OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation

12 Jun 2024arXiv:2407.09498archive 2025-07-28

Yunbei Zhang, Akshay Mehra, Jihun Hamm

Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training phase or modify model parameters at test time through entropy minimization. The former often overlooks unlabeled target data, while the latter doesn't fully address domain shifts. In this work, our approach, Optimal Transport-guided Test-Time Visual Prompting (OT-VP), handles these problems by leveraging prompt learning at test time to align the target and source domains without accessing the training process or altering pre-trained model parameters. This method involves learning a universal visual prompt for the target domain by optimizing the Optimal Transport distance.OT-VP, with only four learned prompt tokens, exceeds state-of-the-art performance across three stylistic datasets-PACS, VLCS, OfficeHome, and one corrupted dataset ImageNet-C. Additionally, OT-VP operates efficiently, both in terms of memory and computation, and is adaptable for extension to online settings.

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="2407.09498")

Code

Syntology Ran 12 of 16 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; 9 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zybeich/ot-vp officialmentioned in papermentioned on GitHubpytorchMIT 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

16 samples harvested; 12 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
9ran
4unverified

Licence: 0 of the 16 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 zybeich/ot-vp. “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.

Classifier zybeich/ot-vp/domainbed/networks.py official repository ran · our draft was wrong MIT (permissive) · ce7990d7ad5821ff · report
compute_conditional_wd zybeich/ot-vp/domainbed/adapt_algorithms.py official repository ran MIT (permissive) · 289f47229057c748 · report
configure_model zybeich/ot-vp/domainbed/adapt_algorithms.py official repository ran MIT (permissive) · 09762c09de098b26 · report
dataloader zybeich/ot-vp/domainbed/lib/torchmisc.py official repository ran MIT (permissive) · 8722522e3721ebfe · report
get_test_records zybeich/ot-vp/domainbed/model_selection.py official repository ran · our draft was wrong MIT (permissive) · 53fac8d8d949e72b · report
grad_reverse zybeich/ot-vp/domainbed/lib/torchmisc.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · b5becb520f35423a · report
hashable zybeich/ot-vp/domainbed/lib/query.py official repository ran fingerprinted MIT (permissive) · 71a3a61ceed99bf3 · report
l2_between_dicts zybeich/ot-vp/domainbed/lib/misc.py official repository ran MIT (permissive) · 1fdaff04251a0d51 · report
make_selector_fn zybeich/ot-vp/domainbed/lib/query.py official repository ran MIT (permissive) · 2f8af5779e1edcb6 · report
make_weights_for_balanced_classes zybeich/ot-vp/domainbed/lib/misc.py official repository ran MIT (permissive) · 3cb172d2f57f12cf · report
net_dist zybeich/ot-vp/domainbed/lib/torchmisc.py official repository ran MIT (permissive) · d3981d403538b1d3 · report
remove_batch_norm_from_resnet zybeich/ot-vp/domainbed/networks.py official repository ran MIT (permissive) · 196cab71d7129d62 · report
get_algorithm_class zybeich/ot-vp/domainbed/adapt_algorithms.py official repository unverified MIT (permissive) · b0bc80b1655a6802 · report
get_dataset_class zybeich/ot-vp/domainbed/datasets.py official repository unverified MIT (permissive) · d0ea85d74c20dea9 · report
num_environments zybeich/ot-vp/domainbed/datasets.py official repository unverified MIT (permissive) · 73f32252eedba6a4 · report
print_row zybeich/ot-vp/domainbed/lib/misc.py official repository unverified MIT (permissive) · 6fe6cf9070a01da7 · report

Tasks

Prompt LearningTest-time AdaptationVisual Prompting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

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