Continual Few-Shot Learning with Adversarial Class Storage
This addresses the challenge of enabling AI systems to learn new tasks continuously without forgetting old knowledge, which is incremental as it builds on existing meta-learning and memory-based approaches.
The paper tackles the problem of continual few-shot learning, where tasks arrive sequentially with limited training samples, by proposing Continual Meta-Learner (CML), which achieves state-of-the-art classification accuracy on datasets like MiniImageNet and CIFAR100 without catastrophic forgetting.
Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges for achieving such human-level intelligence. In this paper, we define a new problem called continual few-shot learning, in which tasks arrive sequentially and each task is associated with a few training samples. We propose Continual Meta-Learner (CML) to solve this problem. CML integrates metric-based classification and a memory-based mechanism along with adversarial learning into a meta-learning framework, which leads to the desirable properties: 1) it can quickly and effectively learn to handle a new task; 2) it overcomes catastrophic forgetting; 3) it is model-agnostic. We conduct extensive experiments on two image datasets, MiniImageNet and CIFAR100. Experimental results show that CML delivers state-of-the-art performance in terms of classification accuracy on few-shot learning tasks without catastrophic forgetting.