This paper addresses the problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes; and several extra novel classes are being considered, each with only a few labeled examples. The model is then evaluated on the overall performance of both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Network, which regularizes the learning of novel classes. In each episode, we train a set of new weights to recognize novel classes until they converge. We demonstrate that the learned attractor network can recognize novel classes while remembering old classes, outperforming baselines that do not rely on an iterative optimization process.

Mengye Ren, Renjie Liao, Ethan Fetaya, Richard S. Zemel

Meta Learning workshop @ NeurIPS 2018

‘Incremental Few-Shot Learning with Attention Attractor Networks’ (PDF)

Uber ATG