Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

ICML 2017 Chelsea FinnPieter AbbeelSergey Levine

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples... (read more)

PDF Abstract
Task Dataset Model Metric name Metric value Global rank Compare
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning MAML Accuracy 48.70% # 15
Few-Shot Image Classification Mini-ImageNet - 5-Shot Learning MAML Accuracy 63.10% # 11
Few-Shot Image Classification OMNIGLOT - 1-Shot Learning MAML Accuracy 98.7% # 3
Few-Shot Image Classification OMNIGLOT - 5-Shot Learning MAML Accuracy 99.9% # 1