Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning
Abstract
Recently, meta-learning has been shown as a promising way to solve few-shot learning. In this paper, inspired by the human cognition process which utilizes both prior-knowledge and vision attention in learning new knowledge, we present a novel paradigm of meta-learning approach with three developments to introduce attention mechanism and prior-knowledge for meta-learning. In our approach, prior-knowledge is responsible for helping meta-learner expressing the input data into high-level representation space, and attention mechanism enables meta-learner focusing on key features of the data in the representation space. Compared with existing meta-learning approaches that pay little attention to prior-knowledge and vision attention, our approach alleviates the meta-learner's few-shot cognition burden. Furthermore, a Task-Over-Fitting (TOF) problem, which indicates that the meta-learner has poor generalization on different K-shot learning tasks, is discovered and we propose a Cross-Entropy across Tasks (CET) metric to model and solve the TOF problem. Extensive experiments demonstrate that we improve the meta-learner with state-of-the-art performance on several few-shot learning benchmarks, and at the same time the TOF problem can also be released greatly.
Cite
@article{arxiv.1812.04955,
title = {Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning},
author = {Yunxiao Qin and Weiguo Zhang and Chenxu Zhao and Zezheng Wang and Xiangyu Zhu and Guojun Qi and Jingping Shi and Zhen Lei},
journal= {arXiv preprint arXiv:1812.04955},
year = {2021}
}
Comments
15 pages