Label Efficient Learning of Transferable Representations acrosss Domains and Tasks
Zelun Luo, Yuliang Zou, Judy Hoffman, Li F Fei-Fei
Abstract
We propose a framework that learns a representation transferable across different domains and tasks in a data efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on labeled source data and unlabeled or sparsely labeled data in the target domain. Our method shows compelling results on novel classes within a new domain even when only a few labeled examples per class are available, outperforming the prevalent fine-tuning approach. In addition, we demonstrate the effectiveness of our framework on the transfer learning task from image object recognition to video action recognition.
BibTeX
@inproceedings{NIPS2017_a8baa565,
author = {Luo, Zelun and Zou, Yuliang and Hoffman, Judy and Fei-Fei, Li F},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Label Efficient Learning of Transferable Representations acrosss Domains and Tasks},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/a8baa56554f96369ab93e4f3bb068c22-Paper.pdf},
volume = {30},
year = {2017}
}