Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Incremental Learning through Deep Adaptation
Amir Rosenfeld, John K. Tsotsos
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a substantial increment in the number of parameters for each added task, typically as many as the original network. We propose a method called Deep Adaptation Networks (DAN) that constrains newly learned filters to be linear combinations of existing ones. DANs preserve performance on the original task, require a fraction (typically 13%) of the number of parameters compared to standard fine-tuning procedures and converge in less cycles of training to a comparable or better level of performance. When coupled with standard network quantization techniques, we further reduce the parameter cost to around 3% of the original with negligible or no loss in accuracy. The learned architecture can be controlled to switch between various learned representations, enabling a single network to solve a task from multiple different domains. We conduct extensive experiments showing the effectiveness of our method on a range of image classification tasks and explore different aspects of its behavior.
TL;DR:An alternative to transfer learning that learns faster, requires much less parameters (3-13 %), usually achieves better results and precisely preserves performance on old tasks.
Keywords:Transfer Learning, Learning without forgetting, Multitask Learning
Enter your feedback below and we'll get back to you as soon as possible.