BriefGPT.xyz
Jun, 2023
耦合变分自编码器
Coupled Variational Autoencoder
HTML
PDF
Xiaoran Hao, Patrick Shafto
TL;DR
本研究提出了基于最优输运理论（OT）的耦合变分自编码器(C-VAE)来克服常规变分自编码器的先验不完整问题，实验结果表明C-VAE在保证数据保真度、潜在向量质量以及生成样本质量方面优于常规VAE、WAE和InfoVAE。
Abstract
variational auto-encoders
are powerful probabilistic models in generative tasks but suffer from generating low-quality samples which are caused by the holes in the prior. We propose the
coupled variational auto-encoder<
→