Cargando…
Wasserstein Uncertainty Estimation for Adversarial Domain Matching
Domain adaptation aims at reducing the domain shift between a labeled source domain and an unlabeled target domain, so that the source model can be generalized to target domains without fine tuning. In this paper, we propose to evaluate the cross-domain transferability between source and target samp...
Autores principales: | Wang, Rui, Zhang, Ruiyi, Henao, Ricardo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9128531/ https://www.ncbi.nlm.nih.gov/pubmed/35620565 http://dx.doi.org/10.3389/fdata.2022.878716 |
Ejemplares similares
-
Fair classification via domain adaptation: A dual adversarial learning approach
por: Liang, Yueqing, et al.
Publicado: (2023) -
Adversarial Robustness of Deep Reinforcement Learning Based Dynamic Recommender Systems
por: Wang, Siyu, et al.
Publicado: (2022) -
Does subnetting and port hardening influence human adversarial decisions? An investigation via a HackIT tool
por: Uttrani, Shashank, et al.
Publicado: (2023) -
Spatial data analysis for intelligent buildings: Awareness of context and data uncertainty
por: Li, Huan, et al.
Publicado: (2022) -
Matching Cases and Controls Using SAS® Software
por: Mortensen, Laura Quitzau, et al.
Publicado: (2019)