Label Efficient Learning of Transferable Representations acrosss Domains and Tasks

Part of Advances in Neural Information Processing Systems 30 (NIPS 2017)

Bibtex »Metadata »Paper »Reviews »

Authors

Zelun Luo, Yuliang Zou, Judy Hoffman, Li F. Fei-Fei

Abstract

<p>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.</p>