BriefGPT.xyz
Sep, 2018
多重对抗领域适应
Multi-Adversarial Domain Adaptation
HTML
PDF
Zhongyi Pei, Zhangjie Cao, Mingsheng Long, Jianmin Wang
TL;DR
本文提出一种多重对抗领域自适应方法(MADA)，能够捕获多模态结构，利用多个领域判别器实现不同数据分布的精细对齐，利用随机梯度下降计算梯度，证据表明该模型在标准领域自适应数据集上优于现有最先进方法。
Abstract
Recent advances in
deep domain adaptation
reveal that
adversarial learning
can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target doma
→