BriefGPT.xyz
Jun, 2021
f域对抗学习:理论与算法
f-Domain-Adversarial Learning: Theory and Algorithms
HTML
PDF
David Acuna, Guojun Zhang, Marc T. Law, Sanja Fidler
TL;DR
本文提出了一种新的通用领域敌对框架,利用变分f-分歧的特征进行领域自适应。基于此框架,推导出了具有重要修正的新算法框架,并证明了其在自然语言和计算机视觉数据集上优于现有的基线结果。
Abstract
unsupervised domain adaptation
is used in many
machine learning
applications where, during training, a model has access to unlabeled data in the target domain, and a related labeled dataset. In this paper, we int
→