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 6592
1x1 Convolution
2013 1987
Grouped Convolution
2012 431
Pointwise Convolution
2016 283
Depthwise Convolution
2016 279
Depthwise Separable Convolution
2017 245
Dilated Convolution
2015 185
3D Convolution
2015 67
Deformable Convolution
2017 42
Invertible 1x1 Convolution
2018 24
Groupwise Point Convolution
2018 23
Masked Convolution
2016 9
Spatially Separable Convolution
2000 8
Octave Convolution
2019 6
CoordConv
2018 6
Submanifold Convolution
2017 4
Selective Kernel Convolution
2019 3
MixConv
2019 3
Deformable Kernel
2019 2
CondConv
2019 2
Active Convolution
2017 2
Attention-augmented Convolution
2019 1
DimConv
2019 1
Depthwise Dilated Separable Convolution
2018 1