Results 251 to 260 of about 3,020,093 (290)
Unsupervised domain adaptation with progressive adaptation of subspaces
Pattern Recognition, 2022 Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift. Most of the existing UDA methods try to mitigate the adverse impact induced by the shift via reducing domain discrepancy.
Songcan Chen
exaly +4 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Adaptive Mutual Learning for Unsupervised Domain Adaptation
IEEE Transactions on Circuits and Systems for Video Technology, 2023Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to unlabeled target domain. The semi-supervised method based on mean-teacher framework is one of the main stream approaches. By enforcing consistency constraints, it is hopeful that the teacher network will distill useful source domain knowledge to the student network.
Lihua Zhou +4 more
openaire +2 more sources
Semantic adaptation network for unsupervised domain adaptation
Neurocomputing, 2021Abstract Domain adaptation methods aim at learning transferable model for the unlabeled target domain. Recently, extensive domain adaptation models are proposed to align representations by minimizing distribution distance between different domains or adversarial training manner.
Qiang Zhou, Wen'an Zhou, Shirui Wang
openaire +1 more source
Cluster adaptation networks for unsupervised domain adaptation
Image and Vision Computing, 2021Abstract Domain adaptation is an important technology for transferring source domain knowledge to new, unseen target domains. Recently, domain adaptation models are applied to learn domain invariant representations by minimizing distribution distance or adversarial training in the feature space. However, existing adversarial domain adaptation methods
Qiang Zhou, Wen'an Zhou, Shirui Wang
openaire +2 more sources
Learning adaptive geometry for unsupervised domain adaptation
Pattern Recognition, 2021Abstract Unsupervised domain adaptation is an effective approach to solve the problem of dataset bias. However, most existing unsupervised domain adaptation methods assume that the geometry structures of data distributions are similar in the source and target domains. This assumption is invalid in many practical applications, because the training and
Baoyao Yang, Pong C. Yuen
openaire +1 more source
Adaptive Component Embedding for Unsupervised Domain Adaptation
2019 IEEE International Conference on Multimedia and Expo (ICME), 2019Domain adaptation has obtained considerable interest from the literatures of multimedia, especially in cross-domain knowledge transfer problems. In this paper, we propose an effective yet time-saving approach, named Adaptive Component Embedding (ACE), for unsupervised domain adaptation.
Mengmeng Jing +4 more
openaire +3 more sources
Glocal Alignment for Unsupervised Domain Adaptation
Multimedia Understanding with Less Labeling on Multimedia Understanding with Less Labeling, 2021Traditional unsupervised domain adaptation methods attempt to align source and target domains globally and are agnostic to the categories of the data points. This results in an inaccurate categorical alignment and diminishes the classification performance on the target domain.
Sachin Chhabra +3 more
openaire +1 more source
Unsupervised double weighted domain adaptation
Neural Computing and Applications, 2020Domain adaptation can effectively transfer knowledge between domains with different distributions. Most existing methods use distribution alignment to mitigate the domain shift. But they typically align the marginal and conditional distributions with equal weights. This neglects the relative importance of different distribution alignments.
Jingyao Li 0003 +2 more
openaire +1 more source
Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
IEEE Transactions on Image ProcessingUnsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data distributions across a large gap, we consider to explore the diffusion technique to handle the challenging UDA task ...
Duo Peng +5 more
openaire +2 more sources
Model Uncertainty for Unsupervised Domain Adaptation
2020 IEEE International Conference on Image Processing (ICIP), 2020The key principle of unsupervised domain adaptation is to minimize the divergence between source and target domain. Many recent methods follow this principle to learn domaininvariant features. They train task-specific classifiers to maximize the divergence and feature extractors to minimize the divergence in an adversarial way.
Joonho Lee, Gyemin Lee
openaire +2 more sources