Skip Connection Blocks

Skip Connection Blocks are building blocks for neural networks that feature skip connections. These skip connections 'skip' some layers allowing gradients to better flow through the network. Below you will find a continuously updating list of skip connection blocks:

METHOD YEAR PAPERS
Residual Block
2015 1177
Bottleneck Residual Block
2015 928
Dense Block
2016 218
Inverted Residual Block
2018 170
ResNeXt Block
2016 95
Non-Local Block
2017 53
CBHG
2017 28
Wide Residual Block
2016 28
ShuffleNet Block
2017 22
SRGAN Residual Block
2016 17
Inception-ResNet-v2-B
2016 11
Inception-ResNet-v2-C
2016 11
DV3 Convolution Block
2017 10
Reversible Residual Block
2017 9
DPN Block
2017 8
Pyramidal Bottleneck Residual Unit
2000 7
Pyramidal Residual Unit
2016 7
MelGAN Residual Block
2019 6
FBNet Block
2018 5
Dilated Bottleneck with Projection Block
2018 4
Dilated Bottleneck Block
2018 4
One-Shot Aggregation
2019 3
Big-Little Module
2018 3
Two-Way Dense Layer
2018 3
SqueezeNeXt Block
2018 3
Efficient Channel Attention
2019 3
Res2Net Block
2019 3
Global Context Block
2019 3
Selective Kernel
2019 3
Conditional DBlock
2019 2
DVD-GAN GBlock
2019 2
ParaNet Convolution Block
2019 2
DVD-GAN DBlock
2019 2
GBlock
2019 2
CSPResNeXt Block
2019 2
Elastic Dense Block
2018 2
DBlock
2019 2
Residual SRM
2019 1
EESP
2018 1
NVAE Encoder Residual Cell
2020 1
NVAE Generative Residual Cell
2020 1
Strided EESP
2018 1
Elastic ResNeXt Block
2018 1
Ghost Bottleneck
2019 1
OSA (identity mapping + eSE)
2019 1