Incremental Few-Shot Learning with Attention Attractor Networks

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.

arXiv commentNeurIPS 2019

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Few-Shot Learning with Graph Neural Networks
• FearNet: Brain-Inspired Model for Incremental Learning
• One-shot Learning with Memory-Augmented Neural Networks
• Understanding Short-Horizon Bias in Stochastic Meta-Optimization

Cited by in corpus (6)

• COVID-19 Image Data Collection: Prospective Predictions Are the Future
• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• Large-Scale Long-Tailed Recognition in an Open World
• Recent Advances of Continual Learning in Computer Vision: An Overview
• Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks
• ProtoAttend: Attention-Based Prototypical Learning