paper-with-me

Papers Universal Domain Adaptation

“Universal Domain Adaptation” 태그가 달린 논문 59편 · 필터 해제

GMM-COMET: Continual Source-Free Universal Domain Adaptation via a Mean Teacher and Gaussian Mixture Model-Based Pseudo-Labeling

2026-01-16 · Pascal Schlachter, Bin Yang arxiv

Unsupervised domain adaptation tackles the problem that domain shifts between training and test data impair the performance of neural networks in many real-world applications. Thereby, in realistic scenarios, the source …

Unsupervised Domain AdaptationUniversal Domain Adaptation

Training-Free Label Space Alignment for Universal Domain Adaptation

2025-09-22 · Dujin Lee, Sojung An, Jungmyung Wi, Kuniaki Saito 외 arxiv

Universal domain adaptation (UniDA) transfers knowledge from a labeled source domain to an unlabeled target domain, where label spaces may differ and the target domain may contain private classes. Previous UniDA methods …

Universal Domain Adaptation

E-MLNet: Enhanced Mutual Learning for Universal Domain Adaptation with Sample-Specific Weighting

2025-09-10 · Samuel Felipe dos Santos, Tiago Agostinho de Almeida, Jurandy Almeida arxiv

Universal Domain Adaptation (UniDA) seeks to transfer knowledge from a labeled source to an unlabeled target domain without assuming any relationship between their label sets, requiring models to classify known samples w…

Universal Domain Adaptation

Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency

2025-08-26 · Zhitong Cheng, Yiran Jiang, Yulong Ge, Yufeng Li 외 arxiv

Domain shift, characterized by degraded model performance during transition from labeled source domains to unlabeled target domains, poses a persistent challenge for deploying deep learning systems. Current unsupervised …

Unsupervised Domain AdaptationProtein Structure PredictionUniversal Domain AdaptationComputational Efficiency

Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation

2025-06-04 · AAAI 2025 3 · 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…

Domain AdaptationUniversal Domain Adaptation

Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation

2025-04-16 · Pascal Schlachter, Jonathan Fuss, Bin Yang

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. Online source-free UDA…

Domain AdaptationPseudo LabelUniversal Domain AdaptationUnsupervised Domain Adaptation

Optimal Transport and Adaptive Thresholding for Universal Domain Adaptation on Time Series

2025-03-14 · Romain Mussard, Fannia Pacheco, Maxime Berar, Gilles Gasso 외

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. Few dedicated UniDA methods exist for Time Series (…

Domain AdaptationTime SeriesUniversal Domain Adaptation

Universal Domain Adaptation for Semantic Segmentation

2025-01-01 · CVPR 2025 1 · Seun-An Choe, Keon-Hee Park, Jinwoo Choi, Gyeong-Moon Park

Unsupervised domain adaptation for semantic segmentation (UDA-SS) aims to transfer knowledge from labeled synthetic data (source) to unlabeled real-world data (target). Traditional UDA-SS methods work on the assumpti…

Domain AdaptationPseudo LabelSemantic SegmentationUniversal Domain Adaptation+1

Reducing Source-Private Bias in Extreme Universal Domain Adaptation

2024-10-15 · Hung-Chieh Fang, Po-Yi Lu, Hsuan-Tien Lin

Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without assuming how much the label-sets of the two domains intersect. The goal of UniDA is to ach…

Domain AdaptationSelf-Supervised LearningUniversal Domain Adaptation

Prototypical Partial Optimal Transport for Universal Domain Adaptation

2024-08-02 · Yucheng Yang, Xiang Gu, Jian Sun

Universal domain adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without requiring the same label sets of both domains. The existence of domain and category shift …

Domain AdaptationUniversal Domain Adaptation

Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model

2024-07-19 · Pascal Schlachter, Simon Wagner, Bin Yang

In practice, domain shifts are likely to occur between training and test data, necessitating domain adaptation (DA) to adjust the pre-trained source model to the target domain. Recently, universal domain adaptation (UniD…

Domain AdaptationOut-of-Distribution DetectionUniversal Domain Adaptation

GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

2024-03-21 · Sanqing Qu, Tianpei Zou, Florian Röhrbein, Cewu Lu 외

Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted …

ClusteringContrastive LearningDomain AdaptationSource-Free Domain Adaptation+1

Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias

2024-03-17 · CVPR 2024 1 · Wenyu Zhang, Qingmu Liu, Felix Ong Wei Cong, Mohamed Ragab 외

Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this work, we introduce Universal Semi-Supervise…

Domain AdaptationPseudo LabelSemi-supervised Domain AdaptationUniversal Domain Adaptation

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

2024-03-06 · CVPR 2024 1 · Sanqing Qu, Tianpei Zou, Lianghua He, Florian Röhrbein 외

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 …

Domain AdaptationTransfer LearningUniversal Domain Adaptation

COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptation

2024-01-31 · Pascal Schlachter, Bin Yang

In real-world applications, there is often a domain shift from training to test data. This observation resulted in the development of test-time adaptation (TTA). It aims to adapt a pre-trained source model to the test da…

Domain AdaptationTest-time AdaptationUniversal Domain Adaptation

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

2023-12-13 · Yanzuo Lu, Meng Shen, Andy J Ma, Xiaohua Xie 외

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. Existing UniDA methods ma…

Domain AdaptationTransfer LearningUniversal Domain Adaptation

A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting

2023-12-08 · Jinjing Zhu, Feiyang Ye, Qiao Xiao, Pengxin Guo 외

Despite the progress made in domain adaptation, solving Unsupervised Domain Adaptation (UDA) problems with a general method under complex conditions caused by label shifts between domains remains a formidable task. In th…

Domain AdaptationPartial Domain AdaptationUniversal Domain AdaptationUnsupervised Domain Adaptation

Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP

2023-10-23 · Hyuhng Joon Kim, Hyunsoo Cho, Sang-Woo Lee, Junyeob Kim 외

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. In order to address thes…

Domain AdaptationUniversal Domain Adaptation

Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation

2023-10-09 · Yuxiang Lai, Yi Zhou, Xinghong Liu, Tao Zhou

Universal domain adaptation aims to align the classes and reduce the feature gap between the same category of the source and target domains. The target private category is set as the unknown class during the adaptation p…

Domain AdaptationUniversal Domain Adaptation

COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation

2023-08-21 · Xinghong Liu, Yi Zhou, Tao Zhou, Chun-Mei Feng 외

Universal domain adaptation (UniDA) aims to address domain and category shifts across data sources. Recently, due to more stringent data restrictions, researchers have introduced source-free UniDA (SF-UniDA). SF-UniDA me…

Domain AdaptationFew-Shot LearningLanguage ModellingUniversal Domain Adaptation
1–20 / 59 다음 →