BriefGPT.xyz
Jul, 2018
HybridNet：半监督学习中的分类和重建协同
HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning
HTML
PDF
Thomas Robert, Nicolas Thome, Matthieu Cord
TL;DR
本文介绍了一种新模型：HybridNet，它是一种双分支编码器-解码器架构，利用未标记的图像数据改善图像分类器的泛化性能。它在各种半监督设置中优于现有技术，并提出一种新的训练目标。
Abstract
In this paper, we introduce a new model for leveraging
unlabeled data
to improve generalization performances of
image classifiers
: a two-branch encoder-decoder architecture called
→