Papers › LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

6 Mar 2024CVPR 2024 1arXiv:2403.03421archive 2025-07-28

Sanqing Qu, Tianpei Zou, Lianghua He, Florian Röhrbein, Alois Knoll, Guang Chen, Changjun Jiang

Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to source data, which tends to be more practical due to data protection policies. The main challenge lies in determining whether covariate-shifted samples belong to target-private unknown categories. Existing methods tackle this either through hand-crafted thresholding or by developing time-consuming iterative clustering strategies. In this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify target-private data. Technically, LEAD initially leverages the orthogonal decomposition analysis for feature decomposition. Then, LEAD builds instance-level decision boundaries to adaptively identify target-private data. Extensive experiments across various UniDA scenarios have demonstrated the effectiveness and superiority of LEAD. Notably, in the OPDA scenario on VisDA dataset, LEAD outperforms GLC by 3.5% overall H-score and reduces 75% time to derive pseudo-labeling decision boundaries. Besides, LEAD is also appealing in that it is complementary to most existing methods. The code is available at https://github.com/ispc-lab/LEAD.

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="2403.03421")

Code

Syntology Ran 9 of 11 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 6 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 1 ran; community (archive-listed): 9 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ispc-lab/lead officialmentioned in papermentioned on GitHubpytorchMIT report
ispc-lab/glc 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

11 samples harvested; 9 ran; 0 honoured the contract we drafted; 2 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.

6ran · our draft was wrong
3ran
2unverified

Licence: 9 of the 11 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.

set_logger ispc-lab/lead/utils/net_utils.py official repository ran MIT (permissive) · 218cf492f8713f71 · report
obtain_LEAD_pseudo_labels ispc-lab/lead/train_target.py official repository unverified MIT (permissive) · f64aa135fdd5f173 · report
Entropy ispc-lab/glc/utils/net_utils.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 94b5622f0aa7add1 · report
log_args ispc-lab/glc/utils/net_utils.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · a7928c7cf111366a · report
lr_scheduler ispc-lab/glc/train_source.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 0b7ffc9f8b77529c · report
op_copy ispc-lab/glc/train_source.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 93a11f62e4a129f0 · report
set_logger ispc-lab/glc/utils/net_utils.py community (archive-listed) ran no licence file found · pointer only · 59fb5d13731e4308 · report
test_transform ispc-lab/glc/dataset/dataset.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 13b7b1c692c187e0 · report
train ispc-lab/glc/train_source.py community (archive-listed) ran no licence file found · pointer only · e4b2648a312cebb6 · report
train_transform ispc-lab/glc/dataset/dataset.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · ada9656c14c75934 · report
obtain_global_pseudo_labels ispc-lab/glc/train_target.py community (archive-listed) unverified no licence file found · pointer only · 5b48697e26a31d82 · report

Tasks

Domain AdaptationTransfer LearningUniversal Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Universal Domain Adaptation DomainNet LEAD H-Score 50.8 #6 of 12 Archive leaderboard report
Universal Domain Adaptation DomainNet LEAD Source-free yes #6 of 12 Archive leaderboard report
Universal Domain Adaptation Office-31 LEAD H-score 87.8 #6 of 12 Archive leaderboard report
Universal Domain Adaptation Office-31 LEAD Source-Free yes #6 of 12 Archive leaderboard report
Universal Domain Adaptation Office-Home LEAD H-Score 75.0 #8 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home LEAD Source-free yes #8 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home LEAD VLM no #8 of 14 Archive leaderboard report
Universal Domain Adaptation VisDA2017 LEAD H-score 76.6 #2 of 13 Archive leaderboard report
Universal Domain Adaptation VisDA2017 LEAD Source-free yes #2 of 13 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