基于混合高斯分布的广义零样本识别  

A Method for Generalized Zero-shot Learning Based on Gaussian Mixture Distribution

作　　者：邵洁 李晓瑞 SHAO Jie;LI Xiaorui(School of Electronics and Information Engineering,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力大学电子与信息工程学院,上海200090

出　　处：《上海电力大学学报》2021年第5期475-480,共6页Journal of Shanghai University of Electric Power

摘　　要：与传统零样本识别相比,广义零样本识别的样本不仅包括测试类别样本,还包括训练类别样本,因此,广义零样本识别更具有现实意义。提出了一种基于混合高斯分布的广义零样本识别的算法(MGM VAE),在编码器中采用多个通道结构,促使变分自编码器(VAE)模型可以在更广泛的空间内寻求更好的映射解。Compared with the traditional zero-shot learning,generalized zero-shot learning includes the test category and the training category.Therefore,generalized zero-shot learning is more realistic.This paper proposes a generalized zero-shot learning algorithm based on a Gaussian mixture distribution(MGM-VAE).Multi-channel structures is used in the encoder,so that the variational auto encoding(VAE)model can seek a better mapping solution in a wider space.

关 键 词：广义零样本识别 混合高斯模型 变分自编码器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]