We propose a framework that learns a representation transferable across different domains and tasks in a label 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.
@article{arxiv.1712.00123,
title = {Label Efficient Learning of Transferable Representations across Domains and Tasks},
author = {Zelun Luo and Yuliang Zou and Judy Hoffman and Li Fei-Fei},
journal= {arXiv preprint arXiv:1712.00123},
year = {2017}
}