Label Efficient Learning of Transferable Representations across Domains and Tasks
This work addresses label-efficient transfer learning for domains like image and video recognition, though it appears incremental as it builds on existing adversarial and metric learning techniques.
The paper tackles the problem of learning representations that can transfer across domains and tasks with limited labeled data, achieving compelling results on novel classes in new domains using only a few labeled examples per class and outperforming fine-tuning approaches.
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.