1Video Analytics Lab, Indian Institute of Science 2Google Research
We introduce concurrent subsidiary supervised DA that not only improves unsupervised goal DA but also facilitates source-free DA. We provide theoretical insights for a suitability criteria to identify DA-assistive subsidiary tasks.
If you find our work helpful in your research, please cite our work:
@InProceedings{kundu2022concurrent,
title={Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation},
author={Kundu, Jogendra Nath and Bhambri, Suvaansh and Kulkarni, Akshay and Sarkar, Hiran and Jampani, Varun and Babu, R. Venkatesh},
booktitle={European Conference on Computer Vision},
year={2022},
}
This project is licenced under an [MIT License].
If you have any queries, please get in touch via email : jogendranathkundu@gmail.com