Methods > Computer Vision

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 8595
1x1 Convolution
2013 2674
Grouped Convolution
2012 452
Pointwise Convolution
2016 448
Depthwise Convolution
2016 439
Depthwise Separable Convolution
2017 393
Dilated Convolution
2015 284
3D Convolution
2015 107
Non-Local Operation
2017 78
Deformable Convolution
2017 59
Invertible 1x1 Convolution
2018 33
SAC
2020 28
Groupwise Point Convolution
2018 27
Transposed convolution
2016 17
Masked Convolution
2016 11
Spatially Separable Convolution
2000 9
Sparse Convolutions
2014 8
Octave Convolution
2019 7
CoordConv
2018 7
(2+1)D Convolution
2017 7
1D CNN
2020 6
Selective Kernel Convolution
2019 5
MixConv
2019 5
Submanifold Convolution
2017 4
CondConv
2019 3
Deformable Kernel
2019 3
DynamicConv
2019 3
Attention-augmented Convolution
2019 2
Depthwise Dilated Separable Convolution
2018 2
Active Convolution
2017 2
Feature-Centric Voting
2015 2
DAU-ConvNet
2019 2
Local Relation Layer
2019 1
DimConv
2019 1
LightConv
2019 1
CP conv
2021 1
CKConv
2021 0