Training few-shot classification via the perspective of minibatch and pretraining
This work provides an incremental improvement for researchers in few-shot learning by speeding up training processes.
The paper tackled few-shot classification by reformulating it as a supervised learning problem and introduced multi-episode and cross-way training techniques, which accelerated training by up to 10 times without accuracy loss on Omniglot and miniImageNet datasets.
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.