Training few-shot classification via the perspective of minibatch and pretraining
Abstract
Few-shot classification is a challenging task which aims to formulate the ability of humans to learn concepts from limited prior data and has drawn considerable attention in machine learning. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained to learn the ability of handling classification tasks on extremely large or infinite episodes representing different classification task, each with a small labeled support set and its corresponding query set. In this work, we advance this few-shot classification paradigm by formulating it as a supervised classification learning problem. We further propose multi-episode and cross-way training techniques, which respectively correspond to the minibatch and pretraining in classification problems. Experimental results on a state-of-the-art few-shot classification method (prototypical networks) demonstrate that both the proposed training strategies can highly accelerate the training process without accuracy loss for varying few-shot classification problems on Omniglot and miniImageNet.
Cite
@article{arxiv.2004.05910,
title = {Training few-shot classification via the perspective of minibatch and pretraining},
author = {Meiyu Huang and Xueshuang Xiang and Yao Xu},
journal= {arXiv preprint arXiv:2004.05910},
year = {2020}
}
Comments
arXiv admin note: text overlap with arXiv:1803.00676 by other authors