Subsidiary Prototype Alignment for Universal Domain Adaptation
NeurIPS 2022
Jogendra Nath Kundu*1 Suvaansh Bhambri*1 Akshay Kulkarni*1 Hiran Sarkar1
Varun Jampani2 R. Venkatesh Babu1
1Video Analytics Lab, Indian Institute of Science 2Google Research
We address negative-transfer in Universal DA with BoW-inspired word-prototypes and subsidiary alignment via a word-related pretext task.
Summary Video
Citation
If you find our work helpful in your research, please cite our work:
@InProceedings{kundu2022subsidiary,
title={Subsidiary Prototype Alignment for Universal Domain Adaptation},
author={Kundu, Jogendra Nath and Bhambri, Suvaansh and Kulkarni, Akshay and Sarkar, Hiran and Jampani, Varun and Babu, R. Venkatesh},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2022},
}
License
This project is licenced under an [MIT License].
Contact
If you have any queries, please get in touch via email : jogendranathkundu@gmail.com