Results 1 to 10 of about 1,321,207 (310)
Multi-Source Distilling Domain Adaptation [PDF]
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 +9 more
openaire +4 more sources
Generalized Source-free Domain Adaptation [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 Accepted by ICCV 2021; Update the acknowledgement ...
Shiqi Yang 0002 +4 more
openaire +5 more sources
Unsupervised multi-source domain adaptation with no observable source data. [PDF]
PLoS ONE, 2021 Given trained models from multiple source domains, how can we predict the labels of unlabeled data in a target domain? Unsupervised multi-source domain adaptation (UMDA) aims for predicting the labels of unlabeled target data by transferring the ...
Hyunsik Jeon, Seongmin Lee, U Kang
doaj +2 more sources
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 +4 more
openaire +4 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
openaire +6 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 +4 more
openaire +2 more sources
“PEOPLE MATTER. FREEDOM MATTERS. PEACE MATTERS”: CONCEPTUAL METAPHOR ANALYSIS OF VOLODYMYR ZELENSKYY’S SPEECHES [PDF]
Вісник університету ім. А. Нобеля. Серія Філологічні науки, 2023 This article draws upon the investigation of distinctive features in Volodymyr Zelenskyy’s speeches delivered during the period of the Russian invasion that started on 24 February 2022 and one month after it.
Anastasiia S. Skichko +2 more
doaj +1 more source
Comparative Study of Intertexts in Newspaper Headlines (Based on the Material of the Russian and British Discourses of Sanctions Policy Towards Russia) [PDF]
Актуальные проблемы филологии и педагогической лингвистики, 2021 The article presents a comparative analysis of intertexts in the headlines of British and Russian articles, the subject of which is the sanctions imposed by Western countries on Russia.
Anastasia S. Podolko
doaj +1 more source
Unified Source-Free Domain Adaptation [PDF]
CoRRIn 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 +4 more
openaire +3 more sources
The metaphorical conceptualization of God in the Serbian language [PDF]
Baština, 2021 The subject of this paper is a way of conceptualizing God in the Serbian language. The aim of the paper is to show and indicate the ways in which the meaning of the noun God is understood in the Serbian language, and which metaphors arise when it is ...
Stevanović Katarina Z.
doaj +1 more source