Search Results for author: Nishank Lakkakula

Found 1 papers, 1 papers with code

UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation

1 code implementation ICCV 2019 Jogendra Nath Kundu, Nishank Lakkakula, R. Venkatesh Babu

In this paper, we propose UM-Adapt - a unified framework to effectively perform unsupervised domain adaptation for spatially-structured prediction tasks, simultaneously maintaining a balanced performance across individual tasks in a multi-task setting.

Multi-Task Learning Representation Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.