BriefGPT.xyz
Nov, 2015
深度卷积生成对抗网络的无监督表示学习
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
HTML
PDF
Alec Radford, Luke Metz, Soumith Chintala
TL;DR
该论文提出深度卷积生成对抗网络（DCGANs）可以用于无监督学习，通过在各种图像数据集上的训练，证明了DCGANs能够学习从物体部分到场景的表示层次结构，并且可以用于一般图像表示。
Abstract
In recent years,
supervised learning
with
convolutional networks
(CNNs) has seen huge adoption in computer vision applications. Comparatively,
un
→