首页|Researcher’s Work from Hefei University of Technology Focuses on Data Intelligen ce (Multi-view Feature Learning for the Over-penalty in Adversarial Domain Adapt ation)
Researcher’s Work from Hefei University of Technology Focuses on Data Intelligen ce (Multi-view Feature Learning for the Over-penalty in Adversarial Domain Adapt ation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on da ta intelligence. According to news reporting from Hefei, People’s Republic of Ch ina, by NewsRx journalists, research stated, “ABSTRACT: Domain adaptation aims t o transfer knowledge from the labeled source domain to an unlabeled target domai n that follows a similar but different distribution.” Our news journalists obtained a quote from the research from Hefei University of Technology: “Recently, adversarial-based methods have achieved remarkable succe ss due to the excellent performance of domaininvariant feature presentation lea rning. However, the adversarial methods learn the transferability at the expense of the discriminability in feature representation, leading to low generalizatio n to the target domain. To this end, we propose a Multi-view Feature Learning me thod for the Over-penalty in Adversarial Domain Adaptation. Specifically, multi- view representation learning is proposed to enrich the discriminative informatio n contained in domain-invariant feature representation, which will counter the o ver-penalty for discriminability in adversarial training.”
Hefei University of TechnologyHefeiP eople’s Republic of ChinaAsiaData IntelligenceMachine Learning
NETL
NSTL
