接头(建筑物)
计算机科学
学习迁移
联合概率分布
领域(数学分析)
人工智能
域适应
随机梯度下降算法
适应(眼睛)
梯度下降
深度学习
传输(计算)
对抗制
机器学习
算法
人工神经网络
数学
统计
工程类
物理
建筑工程
数学分析
光学
并行计算
分类器(UML)
作者
Mingsheng Long,Zhu Han,Jianmin Wang,Michael I. Jordan
出处
期刊:Cornell University - arXiv
日期:2016-05-21
被引量:48
摘要
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain. In this paper, we present joint adaptation networks (JAN), which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domains based on a joint maximum mean discrepancy (JMMD) criterion. Adversarial training strategy is adopted to maximize JMMD such that the distributions of the source and target domains are made more distinguishable. Learning can be performed by stochastic gradient descent with the gradients computed by back-propagation in linear-time. Experiments testify that our model yields state of the art results on standard datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI