Continual Few-Shot Learning with Adversarial Class Storage
Abstract
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.
Cite
@article{arxiv.2207.12303,
title = {Continual Few-Shot Learning with Adversarial Class Storage},
author = {Kun Wu and Chengxiang Yin and Jian Tang and Zhiyuan Xu and Yanzhi Wang and Dejun Yang},
journal= {arXiv preprint arXiv:2207.12303},
year = {2022}
}
Comments
9 pages