Residual Networks
Residual Networks is a deep neural network architecture that belongs to the class of feedforward convolutional networks and is distinguished by its use of residual blocks, which introduce skip connections to enable direct gradient propagation and facilitate the training of extremely deep models by learning residual functions with reference to the layer inputs.
2.5K
Publications
534.2K
Citations
8.8K
Authors
1.9K
Institutions
Publications per year
2017–2026
2.4K
Parents
2.5K
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Mark Sandler, Andrew Howard, Menglong Zhu et al. · 2018 · 25.4K citations
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke et al. · 2017 · 12.6K citations · Full text
Aggregated Residual Transformations for Deep Neural Networks
Saining Xie, Ross Girshick, Piotr Dollár et al. · 2017 · 11.9K citations
1–5 of 2.5K
8.8K
9
h-index
8
h-index
8
h-index
8
h-index
8
h-index
1–5 of 8.8K
1.9K

Chinese Academy of Sciences
Beijing, China
40 h-index
231 publications
19.7K citations
University of Chinese Academy of Sciences
Beijing, China
33 h-index
119 publications
11.1K citations
Tsinghua University
Beijing, China
30 h-index
149 publications
20.7K citations

Harbin Institute of Technology
Harbin, China
27 h-index
85 publications
29.4K citations

Xidian University
Xi'an, China
24 h-index
98 publications
5.5K citations
Wuhan University
Wuhan, China
24 h-index
108 publications
11.8K citations

Zhejiang University
Hangzhou, China
23 h-index
87 publications
5.8K citations

Shanghai Jiao Tong University
Shanghai, China
23 h-index
93 publications
5.6K citations
1–8 of 1.9K
Repository · 298 publications · 46.8K citations
78
h-index
146 publications · 9K citations
46
h-index
45 publications · 5.5K citations
31
h-index
56 publications · 3.2K citations
30
h-index
36 publications · 2K citations
24
h-index
1–5