BriefGPT.xyz
Jun, 2018
循环一致性对抗学习作为近似贝叶斯推断
Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
HTML
PDF
Louis C. Tiao, Edwin V. Bonilla, Fabio Ramos
TL;DR
本文利用拉丁变量模型和贝叶斯推理方法，提出了一种隐式拉丁变量模型的变分推理算法，用于解决缺少成对数据时的领域间对应关系的学习问题，并证明了该算法是近似贝叶斯推理方法的CYCLEGAN模型的特例。
Abstract
We formalize the problem of learning
interdomain correspondences
in the absence of paired data as
bayesian inference
in a
latent variable model
→