Incremental Few-Shot Learning with Attention Attractor Networks

TL;DR

This paper introduces Attention Attractor Networks for incremental few-shot learning, enabling recognition of new classes with limited data without retraining on the entire dataset, by leveraging meta-learning and recurrent back-propagation.

Contribution

It proposes a novel meta-learning model that regularizes learning of new classes and uses recurrent back-propagation to improve incremental few-shot classification performance.

Findings

Outperforms baseline methods in recognizing novel classes

Maintains performance on base classes without retraining

Effectively learns from limited examples

Abstract

Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many applications, it is often desirable to have the flexibility of learning additional concepts, with limited data and without re-training on the full training set. This paper addresses this 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. After learning the novel classes, the model is then evaluated on the overall classification performance on 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, and we show that the technique of recurrent back-propagation can back-propagate through the optimization process and facilitate the learning of these parameters. We demonstrate that the learned attractor network can help recognize novel classes while remembering old classes without the need to review the original training set, outperforming various baselines.