Results 11 to 20 of about 7,549,002 (298)

Discovering Domain Disentanglement for Generalized Multi-Source Domain Adaptation [PDF]

2022 IEEE International Conference on Multimedia and Expo (ICME), 2022
A typical multi-source domain adaptation (MSDA) approach aims to transfer knowledge learned from a set of labeled source domains, to an unlabeled target domain. Nevertheless, prior works strictly assume that each source domain shares the identical group of classes with the target domain, which could hardly be guaranteed as the target label space is not
Zixin Wang, Yadan Luo, Peng-Fei Zhang 0001, Sen Wang 0001, Zi Huang   +4 more
core   +8 more sources

Multi-Source Distilling Domain Adaptation

Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution.
Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu 0013, Runbo Hu, Hua Chai, Kurt Keutzer   +9 more
openaire   +5 more sources

Multi-Source Attention for Unsupervised Domain Adaptation [PDF]

Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2020
Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suitable single source to adapt from, and one must consider multiple sources.
Cui, Xia, Bollegala, Danushka
core   +9 more sources

Unified Source-Free Domain Adaptation [PDF]

CoRR
In the pursuit of transferring a source model to a target domain without access to the source training data, Source-Free Domain Adaptation (SFDA) has been extensively explored across various scenarios, including Closed-set, Open-set, Partial-set, and Generalized settings.
Song Tang 0001, Wenxin Su, Mao Ye 0001, Jianwei Zhang 0001, Xiatian Zhu   +4 more
core   +4 more sources

Domain Adaptation Without Source Data [PDF]

IEEE Transactions on Artificial Intelligence, 2021
Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real-world and possibly causes data-privacy issues, especially when the label of the source domain can be a sensitive attribute as an identifier.
Youngeun Kim, Donghyeon Cho, Kyeongtak Han, Priyadarshini Panda, Sungeun Hong   +4 more
openaire   +2 more sources

Domain Adaptive Semantic Segmentation without Source Data [PDF]

, 2021
Domain adaptive semantic segmentation is recognized as a promising technique to alleviate the domain shift between the labeled source domain and the unlabeled target domain in many real-world applications, such as automatic pilot.
Chen, Zhi, Zhu, Lei, Zhi Chen, You, Fuming, Jingjing Li, Fuming You, Huang, Zi, Zi Huang, Lei Zhu, Li, Jingjing   +9 more
core   +1 more source

Reconstruction of a volumetric source domain [PDF]

Journal of Computational Methods in Sciences and Engineering, 2019
Inverse and ill-posed problems which consist of reconstructing the unknown support of a three-dimensional volumetric source from a single pair of exterior boundary Cauchy data are investigated. The underlying dependent variable may satisfy the Laplace, Poisson, Helmholtz or modified Helmholtz equations.
Bin-Mohsin, B, Lesnic, D
openaire   +3 more sources

Improving Domain Adaptation by Source Selection [PDF]

2019 IEEE International Conference on Image Processing (ICIP), 2019
Domain adaptation consists in learning from a source data distribution a model that will be used on a different target data distribution. The domain adaptation procedure is usually unsuccessful if the source domain is too different from the target one. In this paper, we study domain adaptation for image classification with deep learning in the context ...
Bascol, Kevin, Emonet, Rémi, Fromont, Elisa   +2 more
openaire   +1 more source

Gated Domain Units for Multi-source Domain Generalization.

Trans. Mach. Learn. Res., 2022
ISSN:2835 ...
Simon Föll, Alina Dubatovka, Eugen Ernst, Siu Lun Chau, Martin Maritsch, Patrik Okanovic, Gudrun Thäter, Joachim M. Buhmann, Felix Wortmann, Krikamol Muandet   +9 more
openaire   +4 more sources

Domain Attention Consistency for Multi-Source Domain Adaptation

Proceedings of the British Machine Vision Conference 2021, 2021
Accepted to BMVC 2021 as oral ...
Zhongying Deng, Kaiyang Zhou, Yongxin Yang, Tao Xiang 0002   +3 more
openaire   +4 more sources