Image Feature Extractors

Image Feature Extractors are functions or modules that can be used to learn representations from images. The most common type of feature extractor is a convolution where a kernel slides over the image, allowing for parameter sharing and translation invariance. Below you can find a continuously updating list of image feature extractors.

METHOD YEAR PAPERS
Convolution
1980 6800
1x1 Convolution
2013 2045
Grouped Convolution
2012 423
Pointwise Convolution
2016 293
Depthwise Convolution
2016 289
Depthwise Separable Convolution
2017 254
Dilated Convolution
2015 193
3D Convolution
2015 71
Non-Local Operation
2017 56
Deformable Convolution
2017 47
Invertible 1x1 Convolution
2018 25
Groupwise Point Convolution
2018 21
Masked Convolution
2016 9
Spatially Separable Convolution
2000 9
CoordConv
2018 6
Octave Convolution
2019 5
Submanifold Convolution
2017 4
DynamicConv
2019 3
MixConv
2019 3
Selective Kernel Convolution
2019 3
Deformable Kernel
2019 2
CondConv
2019 2
Active Convolution
2017 2
Depthwise Dilated Separable Convolution
2018 2
LightConv
2019 1
Attention-augmented Convolution
2019 1
DimConv
2019 1
Local Relation Layer
2019 0