Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (I) metric-based, (II) memory-based, (III), and learning-based methods. Finally, current challenges and insights for future researches are discussed.

翻译：尽管深度学习在学习更深层多维数据方面取得了惊人成功，但其在新未见任务上的性能有所下降，这主要归因于其对同分布预测的侧重。此外，深度学习因从少量样本中泛化能力差而闻名。元学习是一种有前景的方法，通过适应少样本数据集的新任务来解决这些问题。本综述首先简要介绍元学习，然后深入探讨最先进的元学习方法及近期进展，涵盖：（一）基于度量的方法、（二）基于记忆的方法、以及（三）基于学习的方法。最后，讨论了当前面临的挑战及对未来研究的见解。