Densely Connected Convolutional Networks.pdf


立即下载 甲基蓝
2024-03-10
net layer layers Dense close convolutional works work subsequent 机器
1.2 MB

Densely Connected Convolutional Networks
Gao Huang∗
Cornell University
gh349@cornell.edu
Zhuang Liu∗
Tsinghua University
liuzhuangthu@gmail.com
Kilian Q. Weinberger
Cornell University
kqw4@cornell.edu
Laurens van der Maaten
Facebook AI Research
lvdmaaten@fb.com
Abstract
Recent work has shown that convolutional networks can
be substantially deeper, more accurate, and efficient to train
if they contain shorter connections between layers close to
the input and those close to the output. In this paper, we
embrace this observation and introduce the Dense Convo-
lutional Network (DenseNet), which connects each layer
to every other layer in a feed-forward fashion. Whereas
traditional convolutional networks with L layers have L
connections—one between each layer and its subsequent
layer—our network has L(L+1)2 direct connections. For
each layer, the feature-maps of all preceding layers are
used as inputs, and its own feature-maps are used as inputs
into all subsequent


net/layer/layers/Dense/close/convolutional/works/work/subsequent/机器/ net/layer/layers/Dense/close/convolutional/works/work/subsequent/机器/
-1 条回复
登录 后才能参与评论
-->