Search Results for author:
Found 2 papers, 0 papers with code
Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
In this paper, we propose the Re-weighted Adversarial Adaptation Network (RAAN) to reduce the feature distribution divergence and adapt the classifier when domain discrepancies are disparate.
Multi-Task Adversarial Network for Disentangled Feature Learning
The encoder and the discriminators are trained cooperatively on factors of interest, but in an adversarial way on factors of distraction.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
