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.

arXiv commentarXiv admin note: text overlap with arXiv:1803.00676 by other authors

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Prototypical Networks for Few-shot Learning
• Theoretical Models of Learning to Learn
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Optimal Distributed Online Prediction using Mini-Batches
• On First-Order Meta-Learning Algorithms
• Meta-Learning with Latent Embedding Optimization
• Rethinking ImageNet Pre-training
• Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
• First-order Methods Almost Always Avoid Saddle Points