Abstract

Domain adaptation is essential to enable wide usage of deep learning based networkstrained using large labeled datasets. Adversarial learning based techniques have showntheir utility towards solving this problem using a discriminator that ensures source andtarget distributions are close. However, here we suggest that rather than using a pointestimate, it would be useful if a distribution based discriminator could be used to bridgethis gap. This could be achieved using multiple classifiers or using traditional ensemblemethods. In contrast, we suggest that a Monte Carlo dropout based ensemble discrim-inator could suffice to obtain the distribution based discriminator. Specifically, we pro-pose a curriculum based dropout discriminator that gradually increases the variance ofthe sample based distribution and the corresponding reverse gradients are used to alignthe source and target feature representations. The detailed results and thorough ablationanalysis show that our model outperforms state-of-the-art results.

Code Released!

BibTex

@article{kurmi2019curriculum,
title={Curriculum based Dropout Discriminator for Domain Adaptation},
author={Kurmi, Vinod Kumar and Bajaj, Vipul and Subramanian, Venkatesh K and Namboodiri, Vinay P},
journal={arXiv preprint arXiv:1907.10628},
year={2019} }

Acknowledgement

We acknowledge the help provided by Delta Lab members, who have supported us for this research activity.