Densely Connected Convolutional Networks

Gao HuangZhuang LiuLaurens van der MaatenKilian Q. Weinberger

   Papers with code   Abstract  PDF

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 Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
DenseNet-201
78.2%
78.5%
2
DenseNet-161
78.1%
--
3
DenseNet-169
77.6%
77.9%
4
DenseNet-161
77.3%
--
5
DenseNet-201
77.3%
78.5%
6
DenseNet-121
76.5%
76.4%
7
DenseNet-169
75.9%
77.9%
8
DenseNet-121
74.8%
76.4%