Papers › Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

15 Mar 2022CVPR 2022 1arXiv:2203.07740archive 2025-07-28

Yabin Zhang, Minghan Li, Ruihuang Li, Kui Jia, Lei Zhang

Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging visual learning tasks, which can be cast as a feature distribution matching problem. With the assumption of Gaussian feature distribution, conventional feature distribution matching methods usually match the mean and standard deviation of features. However, the feature distributions of real-world data are usually much more complicated than Gaussian, which cannot be accurately matched by using only the first-order and second-order statistics, while it is computationally prohibitive to use high-order statistics for distribution matching. In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space. Particularly, a fast EHM algorithm, named Sort-Matching, is employed to perform EFDM in a plug-and-play manner with minimal cost. The effectiveness of our proposed EFDM method is verified on a variety of AST and DG tasks, demonstrating new state-of-the-art results. Codes are available at https://github.com/YBZh/EFDM.

PaperPDFConference PDFCodeCode 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="2203.07740")

Code

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

By repository: official repository: 14 samples from 1 repository, 3 ran; community (archive-listed): 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ybzh/efdm officialmentioned in papermentioned on GitHubpytorchMIT report
zhongliangguo/acdm mentioned 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; 4 ran; 0 honoured the contract we drafted; 11 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.

1ran · our draft was wrong
2ran · fixture could not drive it
1ran
11unverified

Licence: 0 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

adaptive_instance_normalization YBZh/EFDM/ArbitraryStyleTransfer/function.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 16679a24b9881031 · report
calc_mean_std YBZh/EFDM/ArbitraryStyleTransfer/function.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 38eaf8511dc7bc9c · report
compute_ci95 YBZh/EFDM/DomainGeneralization/imcls/parse_test_res.py official repository ran fingerprinted MIT (permissive) · ba26afd892405335 · report
adaptive_mean_normalization YBZh/EFDM/ArbitraryStyleTransfer/function.py official repository unverified MIT (permissive) · b37397d52a07f40e · report
imagedata_kwargs YBZh/EFDM/DomainGeneralization/reid/default_config.py official repository unverified MIT (permissive) · f0b768ed9d252a84 · report
init_pretrained_weights YBZh/EFDM/DomainGeneralization/reid/models/osnet_db.py official repository unverified MIT (permissive) · bd41824b39412f93 · report
lua_recursive_source YBZh/EFDM/ArbitraryStyleTransfer/torch_to_pytorch.py official repository unverified MIT (permissive) · 56fbe35b933005f0 · report
optimizer_kwargs YBZh/EFDM/DomainGeneralization/reid/default_config.py official repository unverified MIT (permissive) · d3e1b4b879ea0786 · report
osnet_x0_75 YBZh/EFDM/DomainGeneralization/reid/models/osnet_db.py official repository unverified MIT (permissive) · 1991f5d9f34aa70f · report
osnet_x1_0 YBZh/EFDM/DomainGeneralization/reid/models/osnet_db.py official repository unverified MIT (permissive) · 7a3189c6c0125d89 · report
search_sorted YBZh/EFDM/DomainGeneralization/reid/models/mixhm.py official repository unverified MIT (permissive) · 69140e8e79dae940 · report
simplify_source YBZh/EFDM/ArbitraryStyleTransfer/torch_to_pytorch.py official repository unverified MIT (permissive) · 7e2ea00ab6257df1 · report
test_transform YBZh/EFDM/ArbitraryStyleTransfer/view.py official repository unverified MIT (permissive) · 939a94cc6cecc770 · report
videodata_kwargs YBZh/EFDM/DomainGeneralization/reid/default_config.py official repository unverified MIT (permissive) · 977724699467d6ae · report
efdm zhongliangguo/acdm/efdm.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 6d8ec9b9ea1ce367 · report

Tasks

Domain GeneralizationStyle Transfer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Style Transfer StyleBench EFDM CLIP Score 0.561 #7 of 7 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