Curriculum based dropout discriminator for domain adaptation

Vinod Kumar Kurmi, Vipul Bajaj, Venkatesh K. Subramanian, Vinay P. Namboodiri

Research output: Contribution to conferencePaperpeer-review

2 Citations (SciVal)
22 Downloads (Pure)


Domain adaptation is essential to enable wide usage of deep learning based networks trained using large labeled datasets. Adversarial learning based techniques have shown their utility towards solving this problem using a discriminator that ensures source and target distributions are close. However, here we suggest that rather than using a point estimate, it would be useful if a distribution based discriminator could be used to bridge this gap. This could be achieved using multiple classifiers or using traditional ensemble methods. In contrast, we suggest that a Monte Carlo dropout based ensemble discriminator could suffice to obtain the distribution based discriminator. Specifically, we propose a curriculum based dropout discriminator that gradually increases the variance of the sample based distribution and the corresponding reverse gradients are used to align the source and target feature representations. The detailed results and thorough ablation analysis show that our model outperforms state-of-the-art results.

Original languageEnglish
Publication statusPublished - 2020
Event30th British Machine Vision Conference, BMVC 2019 - Cardiff, UK United Kingdom
Duration: 9 Sept 201912 Sept 2019


Conference30th British Machine Vision Conference, BMVC 2019
Country/TerritoryUK United Kingdom

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Curriculum based dropout discriminator for domain adaptation'. Together they form a unique fingerprint.

Cite this