Convolutions

Convolutions are a type of operation that can be used to learn representations from images. They involve a learnable kernel sliding over the image and performing element-wise multiplication with the input. The specification allows for parameter sharing and translation invariance. Below you can find a continuously updating list of convolutions.

METHOD YEAR PAPERS
Convolution
1980 7054
1x1 Convolution
2013 2141
Grouped Convolution
2012 429
Pointwise Convolution
2016 320
Depthwise Convolution
2016 313
Depthwise Separable Convolution
2017 275
Dilated Convolution
2015 205
3D Convolution
2015 75
Deformable Convolution
2017 50
Invertible 1x1 Convolution
2018 29
Groupwise Point Convolution
2018 21
Transposed convolution
2016 11
Masked Convolution
2016 9
Spatially Separable Convolution
2000 9
CoordConv
2018 6
Octave Convolution
2019 5
Sparse Convolutions
2014 5
Selective Kernel Convolution
2019 4
Submanifold Convolution
2017 4
MixConv
2019 3
Deformable Kernel
2019 3
DynamicConv
2019 3
CondConv
2019 2
Active Convolution
2017 2
Depthwise Dilated Separable Convolution
2018 2
Feature-Centric Voting
2015 2
Attention-augmented Convolution
2019 1
DimConv
2019 1
LightConv
2019 1