本文已被：浏览 637次 下载 285次
投稿时间：2020-03-24
投稿时间：2020-03-24
中文摘要: 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。
Abstract: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.
文章编号：20215011 中图分类号：TP391 文献标志码：
基金项目:
引用文本：
邵洁,李晓瑞.基于混合高斯分布的广义零样本识别[J].上海电力大学学报,2021,37(5):475-480.
SHAO Jie,LI Xiaorui.A Method for Generalized Zero-shot Learning Based on Gaussian Mixture Distribution[J].Journal of Shanghai University of Electric Power,2021,37(5):475-480.
邵洁,李晓瑞.基于混合高斯分布的广义零样本识别[J].上海电力大学学报,2021,37(5):475-480.
SHAO Jie,LI Xiaorui.A Method for Generalized Zero-shot Learning Based on Gaussian Mixture Distribution[J].Journal of Shanghai University of Electric Power,2021,37(5):475-480.