no code implementations • ECCV 2020 • Jianfei Yang, Han Zou, Yuxun Zhou, Zhaoyang Zeng, Lihua Xie ()
Adversarial domain adaptation has made tremendous success by learning domain-invariant feature representations.
no code implementations • ICLR 2020 • Jianfei Yang, Han Zou, Yuxun Zhou, Lihua Xie
The proposed MDAT stabilizes the gradient reversing in ARN by replacing the domain classifier with a reconstruction network, and in this manner ARN conducts both feature-level and pixel-level domain alignment without involving extra network structures.
no code implementations • NeurIPS 2016 • Yuxun Zhou, Costas J. Spanos
We study causal subset selection with Directed Information as the measure of prediction causality.