Papers › Do We Really Need to Access the Source Data? Source Hypothesis Transfer for...

Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation

20 Feb 2020ICML 2020 1arXiv:2002.08546archive 2025-07-28

Jian Liang, Dapeng Hu, Jiashi Feng

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model, making them risky and inefficient for decentralized private data. This work tackles a practical setting where only a trained source model is available and investigates how we can effectively utilize such a model without source data to solve UDA problems. We propose a simple yet generic representation learning framework, named Source HypOthesis Transfer (SHOT). SHOT freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis. To verify its versatility, we evaluate SHOT in a variety of adaptation cases including closed-set, partial-set, and open-set domain adaptation. Experiments indicate that SHOT yields state-of-the-art results among multiple domain adaptation benchmarks.

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 (tim-learn/SHOT) is linked to this paper; the 2 samples below are identical to code Syntology harvested from another paper's repository, and this paper's own copy was not located. Syntology harvested code from tim-learn/SHOT for another paper.

tim-learn/SHOT: Syntology's graph links these samples to DINE: Domain Adaptation from Single and Multiple Black-box Predictors (arXiv:2104.01539; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 2 code samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: 2 identical to code first harvested elsewhere. 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 3 of its repositories that Syntology harvested for other papers:

No date is recorded for any of the 2 samples that ran: their levels were written before Syntology's graph kept the date.

tim-learn/SHOT officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DINE: Domain Adaptation from Single and Multiple Black-box Predictors (arXiv:2104.01539; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
AlexisGuichemerreCode/survey_hist_wsol_sfda mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Source-Free Domain Adaptation via Distribution Estimation (arXiv:2204.11257; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Claydon-Wang/OFTTA mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition (arXiv:2310.18562; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 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

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

2ran · our draft was wrong

Licence: 2 of the 2 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.

2 samples are listed last, in a group without a repository. “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.

Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
lr_scheduler in 32 papers repository not located ran · our draft was wrong licence of this copy not recorded · 0b7ffc9f8b77529c · report fixture: signature optimizer:SGD/0/?, iter_num:int/0/int, max_iter:int/0/int, gamma:int/0/int, power:float/0/float · returned SGD · level recorded, date not recorded
op_copy in 17 papers repository not located ran · our draft was wrong licence of this copy not recorded · 93a11f62e4a129f0 · report fixture: signature optimizer:SGD/0/? · returned SGD · level recorded, date not recorded

Tasks

Domain AdaptationPartial Domain AdaptationRepresentation LearningSource-Free Domain AdaptationUniversal Domain AdaptationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation MNIST-to-USPS SHOT Accuracy 98.0 #6 of 14 Archive leaderboard report
Domain Adaptation Office-31 SHOT Average Accuracy 88.6 #22 of 40 Archive leaderboard report
Domain Adaptation Office-Home SHOT Accuracy 71.8 #19 of 29 Archive leaderboard report
Domain Adaptation SVHN-to-MNIST SHOT Accuracy 98.9 #2 of 14 Archive leaderboard report
Domain Adaptation SVNH-to-MNIST SHOT Accuracy 98.9 #2 of 9 Archive leaderboard report
Domain Adaptation USPS-to-MNIST SHOT Accuracy 98.4 #3 of 14 Archive leaderboard report
Domain Adaptation VisDA2017 SHOT Accuracy 82.9 #19 of 28 Archive leaderboard report
Partial Domain Adaptation Office-Home SHOT Accuracy (%) 78.3 #3 of 11 Archive leaderboard report
Source-Free Domain Adaptation VisDA-2017 SHOT Accuracy 82.9 #10 of 10 Archive leaderboard report
Universal Domain Adaptation DomainNet SHOT-O H-Score 32.6 #12 of 12 Archive leaderboard report
Universal Domain Adaptation DomainNet SHOT-O Source-free no #12 of 12 Archive leaderboard report
Universal Domain Adaptation Office-Home SHOT-O H-Score 40.7 #14 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home SHOT-O Source-free yes #14 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home SHOT-O VLM no #14 of 14 Archive leaderboard report
Universal Domain Adaptation VisDA2017 SHOT-O H-score 44.0 #11 of 13 Archive leaderboard report
Universal Domain Adaptation VisDA2017 SHOT-O Source-free yes #11 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.

Methods

Introduced by this paper: Source Hypothesis Transfer

Source Hypothesis Transfer

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