Reducing bias to source samples for unsupervised domain adaptation

DOI10.1016/J.NEUNET.2021.03.021MaRDI QIDQ6079018zbMATH OpenOpenAlexFDO

Authors Yalan Ye, Ziwei Huang, Tongjie Pan, Jingjing Li, Heng Tao Shen

Publication date 28 September 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2021.03.021

zbMATH Keywords

domain adaptationgenerative adversarial networktransfer learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• MapFlow: latent transition via normalizing flow for unsupervised domain adaptation
• Finding robust transfer features for unsupervised domain adaptation
• Unsupervised domain adaptation with non-stochastic missing data
• NaCL: noise-robust cross-domain contrastive learning for unsupervised domain adaptation
• Unsupervised domain adaptation in the wild via disentangling representation learning

Cites work

• A theory of learning from different domains
• Adaptive non-negative projective semi-supervised learning for inductive classification
• Domain-adversarial training of neural networks
• Locality Preserving Joint Transfer for Domain Adaptation
• Visualizing data using t-SNE

Cited in

(4)

• Unsupervised domain adaptation with non-stochastic missing data
• On the Hardness of Domain Adaptation and the Utility of Unlabeled Target Samples
• NaCL: noise-robust cross-domain contrastive learning for unsupervised domain adaptation
• Active domain adaptation with mining diverse knowledge: an updated class consensus dictionary approach

This page was built for publication: Reducing bias to source samples for unsupervised domain adaptation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6079018)