Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Lv, Fangrui"'
Autor:
Zhang, Yiyuan, Gong, Kaixiong, Ding, Xiaohan, Zhang, Kaipeng, Lv, Fangrui, Keutzer, Kurt, Yue, Xiangyu
We propose $\textbf{UniDG}$, a novel and $\textbf{Uni}$fied framework for $\textbf{D}$omain $\textbf{G}$eneralization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models regardless of the
Externí odkaz:
http://arxiv.org/abs/2310.10008
Domain generalization (DG) tends to alleviate the poor generalization capability of deep neural networks by learning model with multiple source domains. A classical solution to DG is domain augmentation, the common belief of which is that diversifyin
Externí odkaz:
http://arxiv.org/abs/2303.13297
Domain generalization (DG) is essentially an out-of-distribution problem, aiming to generalize the knowledge learned from multiple source domains to an unseen target domain. The mainstream is to leverage statistical models to model the dependence bet
Externí odkaz:
http://arxiv.org/abs/2203.14237
Autor:
Lv, Fangrui, Liang, Jian, Gong, Kaixiong, Li, Shuang, Liu, Chi Harold, Li, Han, Liu, Di, Wang, Guoren
Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source. To achieve this, DA methods include a source classification objective to extract
Externí odkaz:
http://arxiv.org/abs/2112.04137
In this paper, we focus on learning effective entity matching models over multi-source large-scale data. For real applications, we relax typical assumptions that data distributions/spaces, or entity identities are shared between sources, and propose
Externí odkaz:
http://arxiv.org/abs/2112.02792
Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature distributions of
Externí odkaz:
http://arxiv.org/abs/2108.05720
Unsupervised domain adaptation challenges the problem of transferring knowledge from a well-labelled source domain to an unlabelled target domain. Recently,adversarial learning with bi-classifier has been proven effective in pushing cross-domain dist
Externí odkaz:
http://arxiv.org/abs/2012.06995
Publikováno v:
In Tribology International September 2023 187
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Ocean Engineering 1 February 2021 221