BriefGPT.xyz
Sep, 2017
一种使用条件变分自编码器进行零样本学习的生成模型
A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders
HTML
PDF
Ashish Mishra, M Shiva Krishna Reddy, Anurag Mittal, Hema A Murthy
TL;DR
这篇文章研究了零样本学习在图像分类中的应用，提出了一种基于条件变分自编码器的生成模型方法，用于模拟未见过的样本，获得更好的分类性能。
Abstract
zero shot learning
in
image classification
refers to the setting where images from some
novel classes
are absent in the training data. Ima
→