Matching Networks for One Shot Learning
Oriol Vinyals Google DeepMind、Charles Blundell Google DeepMind、Timothy Lillicrap Google DeepMind \ANDKoray Kavukcuoglu Google DeepMind、Daan Wierstra Google DeepMind
Abstract
Learning from a few examples remains a key challenge in machine learning. Despite recent advances in important domains such as vision and language, the standard supervised deep learning paradigm does not offer a satisfactory solution for learning new concepts rapidly from little data. In this work, we employ ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories. Our framework learns a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. We then define one-shot learning problems on vision (using Omniglot, ImageNet) and language tasks. Our algorithm improves one-shot accuracy on ImageNet from 87.6% to 93.2% and from 88.0% to 93.8% on Omniglot compared to competing approaches. We also demonstrate the usefulness of the same model on language modeling by introducing a one-shot task on the Penn Treebank.
中文速览
小样本学习长期是机器学习的核心难题——人类只需看一张长颈鹿的图片就能认识它，而深度学习模型往往需要成百上千的样本。本文提出了一种叫做"匹配网络"（Matching Networks）的框架，将度量学习（metric learning）与记忆增强神经网络结合起来，让模型直接学会"拿着少量标注样本去匹配新例子"的能力，而不需要在遇到新类别时重新微调参数。训练时刻意模拟测试场景——每次只给模型看几个样本、不断切换任务类别——使训练与推理条件完全吻合。实验结果表明，该方法在ImageNet单样本识别准确率上从87.6%提升至93.2%，在Omniglot上从88.0%提升至93.8%，并在Penn Treebank语言建模任务上也展示了同样框架的有效性，为少样本学习研究提供了新的基准和思路。
原文 arXiv:1606.04080;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1606.04080v2