Papers › Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation

Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation

4 Jun 2025AAAI 2025 3arXiv:2506.03521archive 2025-07-28

Weinan He, Zilei Wang, Yixin Zhang

Universal Domain Adaptation (UniDA) focuses on transferring source domain knowledge to the target domain under both domain shift and unknown category shift. Its main challenge lies in identifying common class samples and aligning them. Current methods typically obtain target domain semantics centers from an unconstrained continuous image representation space. Due to domain shift and the unknown number of clusters, these centers often result in complex and less robust alignment algorithm. In this paper, based on vision-language models, we search for semantic centers in a semantically meaningful and discrete text representation space. The constrained space ensures almost no domain bias and appropriate semantic granularity for these centers, enabling a simple and robust adaptation algorithm. Specifically, we propose TArget Semantics Clustering (TASC) via Text Representations, which leverages information maximization as a unified objective and involves two stages. First, with the frozen encoders, a greedy search-based framework is used to search for an optimal set of text embeddings to represent target semantics. Second, with the search results fixed, encoders are refined based on gradient descent, simultaneously achieving robust domain alignment and private class clustering. Additionally, we propose Universal Maximum Similarity (UniMS), a scoring function tailored for detecting open-set samples in UniDA. Experimentally, we evaluate the universality of UniDA algorithms under four category shift scenarios. Extensive experiments on four benchmarks demonstrate the effectiveness and robustness of our method, which has achieved state-of-the-art performance.

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

Syntology 11 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 11 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Sapphire-356/TASC officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified 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: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures 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.

8ran
3unverified

Licence: 0 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 Sapphire-356/TASC. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Sapphire-356/TASC official repository 11 samples, 8 ran (0 instrument-failed) · 3 unverified
Metric in 10 papers train_sapphire_TASC.py ran MIT (permissive) · a64a50db3a32fffe · report fixture: signature S_iter:Tensor/3/float, r_iter:Tensor/1/int, image_features:Tensor/2/float, lambda_dict:dict/0/?, ce_prob_temp:float/0/float · returned Tensor · level recorded 2026-09-25
NNConsistencyLoss sapphire/train/loss.py ran MIT (permissive) · b6022f70325a4031 · report fixture: signature indexs:Tensor/1/int, nn_indexs:Tensor/2/int, input:Tensor/2/float, memory_bank:Tensor/2/float, type:str/0/str, label_smooth:float/0/float · returned tuple · level recorded 2026-09-25
aToBSheduler sapphire/models/utils.py ran MIT (permissive) · 07e359b5e4b5c432 · report fixture: signature step:int/0/int, A:float/0/float, B:float/0/float, gamma:int/0/int, max_iter:int/0/int · returned float · level recorded 2026-09-25
find_folders_with_keyword exp_scripts/get_results.py ran fingerprinted MIT (permissive) · 6257214ba37b90f8 · report fixture: signature root_dir:str/0/str, keywords:list/1/str · returned list · level recorded 2026-09-25
find_metric_json_files exp_scripts/get_results.py ran MIT (permissive) · 38a3330d069f724f · report fixture: signature folder:str/0/str · returned list · level recorded 2026-09-25
flatten_json_fields exp_scripts/get_results.py ran MIT (permissive) · 62b8c7b3100d78c8 · report fixture: signature data:dict/0/? · returned dict · level recorded 2026-09-25
get_entropy in 18 papers
census: 7 implementations from 7 papers, 7 distinct outputs across 2 buckets, one shared input per bucket
train_sapphire_TASCBase.py ran MIT (permissive) · 2904c1a5e4c8fd97 · report fixture: signature features:Tensor/2/float, anchors:Tensor/2/float, temp:float/0/float, normalized:bool/0/bool · returned Tensor · level recorded 2026-09-25
unravel_indices train_sapphire_TASCBase.py ran MIT (permissive) · 203cd9f4f03efdfd · report fixture: signature indices:Tensor/2/int, shape:tuple/1/int · returned Tensor · level recorded 2026-09-25
LoRA_ViT sapphire/models/LoRA_layer.py unverified MIT (permissive) · 511c1d694621e88c · report
get_prototypes train_sapphire_TASCBase.py unverified MIT (permissive) · 4f30a84e99b847d7 · report
gmm_threshold train_sapphire_TASC.py unverified MIT (permissive) · 45ced87c694743dd · report

Tasks

Domain AdaptationUniversal Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Universal Domain Adaptation DomainNet TASC H-Score 73.28 #1 of 12 Archive leaderboard report
Universal Domain Adaptation DomainNet TASC Source-free no #1 of 12 Archive leaderboard report
Universal Domain Adaptation Office-Home TASC H-Score 89.44 #1 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home TASC Source-free no #1 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home TASC VLM yes #1 of 14 Archive leaderboard report
Universal Domain Adaptation VisDA2017 TASC H-score 90.36 #1 of 13 Archive leaderboard report
Universal Domain Adaptation VisDA2017 TASC Source-free no #1 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

SET

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