Deep Transfer Learning with Joint Adaptation Networks
Mingsheng Long, Han Zhu, Jianmin Wang, Michael I. Jordan
Abstract
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.
BibTeX
@InProceedings{pmlr-v70-long17a,
title = {Deep Transfer Learning with Joint Adaptation Networks},
author = {Mingsheng Long and Han Zhu and Jianmin Wang and Michael I. Jordan},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {2208--2217},
year = {2017},
editor = {Precup, Doina and Teh, Yee Whye},
volume = {70},
series = {Proceedings of Machine Learning Research},
month = {06--11 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/long17a/long17a.pdf},
url = {https://proceedings.mlr.press/v70/long17a.html},
abstract = {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.}
}