1511.06434.pdf


立即下载 Hey ou
2024-03-26
CNNs con learning. net works convolutional supervised learning deep Research
7.1 MB

Under review as a conference paper at ICLR 2016
UNSUPERVISED REPRESENTATION LEARNING
WITH DEEP CONVOLUTIONAL
GENERATIVE ADVERSARIAL NETWORKS
Alec Radford & Luke Metz
indico Research
Boston, MA
{alec,luke}@indico.io
Soumith Chintala
Facebook AI Research
New York, NY
soumith@fb.com
ABSTRACT
In recent years, supervised learning with convolutional networks (CNNs) has
seen huge adoption in computer vision applications. Comparatively, unsupervised
learning with CNNs has received less attention. In this work we hope to help
bridge the gap between the success of CNNs for supervised learning and unsuper-
vised learning. We introduce a class of CNNs called deep convolutional generative
adversarial networks (DCGANs), that have certain architectural constraints, and
demonstrate that they are a strong candidate for unsupervised learning. Training
on various image datasets, we show convincing evidence that our deep convolu-
tional adversarial pair learns a hierarchy of represent


CNNs/con/learning./net/works/convolutional/supervised/learning/deep/Research/ CNNs/con/learning./net/works/convolutional/supervised/learning/deep/Research/
-1 条回复
登录 后才能参与评论
-->