Methods › Computer Vision › Convolutions

Convolutions

43 methods 20,128 papers tagged archive 2025-07-28

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.

Methods

All 43 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.


Convolution	1980	19,586
1x1 Convolution	–	5,640
Depthwise Convolution	2016	1,321
Pointwise Convolution	2016	1,306
Depthwise Separable Convolution	–	1,174
Dilated Convolution	–	679
Grouped Convolution	–	575
3D Convolution	2015	208
SAC Switchable Atrous Convolution	–	168
Deformable Convolution	–	152
1D CNN 1-Dimensional Convolutional Neural Networks	–	92
Invertible 1x1 Convolution	–	79
Groupwise Point Convolution	–	53
Sparse Convolutions	–	37
Selective Kernel Convolution	–	29
Transposed convolution	–	29
Masked Convolution	–	26
(2+1)D Convolution	–	17
CoordConv	–	16
PDC Prime Dilated Convolution	–	14
MixConv Mixed Depthwise Convolution	–	12
Spatially Separable Convolution	–	12
DynamicConv Dynamic Convolution	–	11
Octave Convolution	–	9
Deformable Kernel	–	8
Submanifold Convolution	–	7
DCLS Dilated convolution with learnable spacings	–	6
Large Kernel Size Large convolutional kernels	–	6
Span-Based Dynamic Convolution	–	6
CondConv	–	5
Depthwise Dilated Separable Convolution	–	4
Feature-Centric Voting	–	4
PP-OCR	–	4
Active Convolution	–	3
Attention-augmented Convolution	–	3
CKConv Continuous Kernel Convolution	–	2
DAU-ConvNet Displaced Aggregation Units	–	2
ShapeConv	–	2
CP conv Center-pivot convolution	–	1
DimConv Dimension-wise Convolution	–	1
Invertible NxN Convolution	–	1
LightConv Lightweight Convolution	–	1
PushPull-Conv Push Pull Convolutions	–	1