Universal Domain Adaptation

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 31 papers with code (55 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Upcycling Models under Domain and Category Shift
  13 Mar 2023 3 repositories listed
  We examine the superiority of our GLC on multiple benchmarks with different category shift scenarios, including partial-set, open-set, and open-partial-set DA.
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
  20 Feb 2020 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain.
• GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
  21 Mar 2024 2 repositories listed
  GLC++ enhances the novel category clustering accuracy of GLC by 4.
• LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
  6 Mar 2024 2 repositories listed Syntology ran 9 of 11 samples · 2 unverified · 9 pointer-only (licence)
  Besides, LEAD is also appealing in that it is complementary to most existing methods.
• OVANet: One-vs-All Network for Universal Domain Adaptation
  7 Apr 2021 2 repositories listed Syntology ran 4 of 12 samples · 8 unverified
  In this paper, we propose a method to learn the threshold using source samples and to adapt it to the target domain.
• Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation
  4 Jun 2025 1 repository listed Syntology ran 0 of 11 samples · 11 unverified
  In this paper, based on vision-language models, we search for semantic centers in a semantically meaningful and discrete text representation space.
• Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation
  16 Apr 2025 1 repository listed
  A domain (distribution) shift between training and test data often hinders the real-world performance of deep neural networks, necessitating unsupervised domain adaptation (UDA) to bridge this gap.
• Optimal Transport and Adaptive Thresholding for Universal Domain Adaptation on Time Series
  14 Mar 2025 1 repository listed
  Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, even when their classes are not fully shared.
• Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model
  19 Jul 2024 1 repository listed
  Recently, universal domain adaptation (UniDA) has gained attention for addressing the possibility of an additional category (label) shift between the source and target domain.
• Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
  17 Mar 2024 1 repository listed
  UniSSDA is at the intersection of Universal Domain Adaptation (UniDA) and Semi-Supervised Domain Adaptation (SSDA): the UniDA setting does not allow for fine-grained categorization of target private classes not…
• COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptation
  31 Jan 2024 1 repository listed
  In real-world applications, there is often a domain shift from training to test data.
• MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
  13 Dec 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer.
• Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP
  23 Oct 2023 1 repository listed
  When deploying machine learning systems to the wild, it is highly desirable for them to effectively leverage prior knowledge to the unfamiliar domain while also firing alarms to anomalous inputs.
• COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation
  21 Aug 2023 1 repository listed
  SF-UniDA methods eliminate the need for direct access to source samples when performing adaptation to the target domain.
• Universal Domain Adaptation from Foundation Models: A Baseline Study
  18 May 2023 1 repository listed
  We hope that our investigation and the proposed simple framework can serve as a strong baseline to facilitate future studies in this field.
• Noisy Universal Domain Adaptation via Divergence Optimization for Visual Recognition
  20 Apr 2023 1 repository listed
  To transfer the knowledge learned from a labeled source domain to an unlabeled target domain, many studies have worked on universal domain adaptation (UniDA), where there is no constraint on the label sets of the source…
• Domain Adaptation for Time Series Under Feature and Label Shifts
  6 Feb 2023 1 repository listed Syntology ran 3 of 17 samples · 14 unverified
  Additionally, the label distributions of tasks in the source and target domains can differ significantly, posing difficulties in addressing label shifts and recognizing labels unique to the target domain.
• DeepAstroUDA: Semi-Supervised Universal Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection
  3 Feb 2023 1 repository listed
  This algorithm performs semi-supervised domain adaptation and can be applied to datasets with different data distributions and class overlaps.
• Universal Domain Adaptation for Remote Sensing Image Scene Classification
  26 Jan 2023 1 repository listed
  Empirical results show that the proposed model is effective and practical for remote sensing image scene classification, regardless of whether the source data is available or not.
• Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier
  1 Jan 2023 1 repository listed
  The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
• Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection
  1 Nov 2022 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  For the first time, we demonstrate the successful use of domain adaptation on two very different observational datasets (from SDSS and DECaLS).
• Unified Optimal Transport Framework for Universal Domain Adaptation
  31 Oct 2022 1 repository listed Syntology ran 1 of 3 samples · 2 unverified
  Notably, UniOT is the first method with the capability to automatically discover and recognize private categories in the target domain for UniDA.
• HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks
  17 Oct 2022 1 repository listed Syntology ran 8 of 16 samples · 8 unverified
  We apply this parameterization to the state-of-art domain adaptation methods and show that it has almost the same expressiveness as the full parameter space.
• OneRing: A Simple Method for Source-free Open-partial Domain Adaptation
  7 Jun 2022 1 repository listed
  In this paper, we investigate Source-free Open-partial Domain Adaptation (SF-OPDA), which addresses the situation where there exist both domain and category shifts between source and target domains.
• VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
  23 Jul 2021 1 repository listed
  Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i.
• Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation
  5 Jul 2021 1 repository listed
  Vision systems trained in closed-world scenarios fail when presented with new environmental conditions, new data distributions, and novel classes at deployment time.
• Domain Consensus Clustering for Universal Domain Adaptation
  5 Jun 2021 1 repository listed
  To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and…
• On Universal Black-Box Domain Adaptation
  10 Apr 2021 1 repository listed
  The great promise that UB²DA makes, however, brings significant learning challenges, since domain adaptation can only rely on the predictions of unlabeled target data in a partially overlapped label space, by accessing…
• Divergence Optimization for Noisy Universal Domain Adaptation
  1 Apr 2021 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Hence, we consider a new realistic setting called Noisy UniDA, in which classifiers are trained with noisy labeled data from the source domain and unlabeled data with an unknown class distribution from the target domain.
• Learning to Detect Open Classes for Universal Domain Adaptation
  1 Aug 2020 1 repository listed
  The new transferability measure accurately quantifies the inclination of a target example to the open classes.

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.