学习组合表示用于少样本识别

Dec, 2018

Learning Compositional Representations for Few-Shot Recognition

Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert

TL;DR通过引入简单的正则化技术以及利用类别级别属性注释对神经网络进行特征空间分解，本工作试图弥合深度学习模型与人类学习之间的鸿沟，证明组合表示的价值并展示少量样本即可学习新类别的分类器。

Abstract

One of the key limitations of modern deep learning based approaches lies in the amount of data required to train them. Humans, on the other hand, can learn to recognize novel categories from just a few examples.