Search Results for author:
Found 3 papers, 0 papers with code
Mind the Discriminability: Asymmetric Adversarial Domain Adaptation
Adversarial domain adaptation has made tremendous success by learning domain-invariant feature representations.
Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training
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.
Causal meets Submodular: Subset Selection with Directed Information
We study causal subset selection with Directed Information as the measure of prediction causality.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
