English

Label Efficient Learning of Transferable Representations across Domains and Tasks

Machine Learning 2017-12-04 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@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}
}

Comments

NIPS 2017

R2 v1 2026-06-22T23:03:11.491Z