Training few-shot classification via the perspective of minibatch and pretraining
Huang, Meiyu, Xiang, Xueshuang, Xu, Yao
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.
Apr-9-2020
- Country:
- Asia
- China (0.04)
- Middle East > Jordan (0.04)
- Europe > Germany
- Bavaria > Upper Bavaria > Munich (0.04)
- Asia
- Genre:
- Research Report (0.82)
- Industry:
- Education (0.34)
- Technology: