Learning Good Features to Transfer Across Tasks and Domains
This work addresses the challenge of deploying deep learning in new domains with limited supervision, though it is incremental as it builds on existing transfer learning methods.
The paper tackles the problem of limited labeled data for deep learning in new domains by learning a mapping between task-specific deep features to enable knowledge transfer across tasks and domains, achieving compelling results in synthetic-to-real adaptation scenarios for tasks like monocular depth estimation and semantic segmentation.
Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests that there should be a way of reusing the knowledge learned in a specific setting to solve novel tasks with limited or no additional supervision. In this work, we first show that such knowledge can be shared across tasks by learning a mapping between task-specific deep features in a given domain. Then, we show that this mapping function, implemented by a neural network, is able to generalize to novel unseen domains. Besides, we propose a set of strategies to constrain the learned feature spaces, to ease learning and increase the generalization capability of the mapping network, thereby considerably improving the final performance of our framework. Our proposal obtains compelling results in challenging synthetic-to-real adaptation scenarios by transferring knowledge between monocular depth estimation and semantic segmentation tasks.