Convolutions

Edit

Computer Vision • Image Feature Extractors • 57 methods

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

Add a Method

Method	Year	Papers
Convolution	1980	16855
1x1 Convolution Network In Network	2013	5073
Depthwise Convolution	2016	1076
Pointwise Convolution	2016	1066
Depthwise Separable Convolution Xception: Deep Learning With Depthwise Separable Convolutions	2017	952
Dilated Convolution Multi-Scale Context Aggregation by Dilated Convolutions	2015	583
Grouped Convolution ImageNet Classification with Deep Convolutional Neural Networks	2012	545
3D Convolution	2015	186
SAC DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution	2020	130
Deformable Convolution Deformable Convolutional Networks	2017	120
Invertible 1x1 Convolution Glow: Generative Flow with Invertible 1x1 Convolutions	2018	71
1D CNN Convolutional Neural Network and Rule-Based Algorithms for Classifying 12-lead ECGs	2020	68
Groupwise Point Convolution ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network	2018	51
Sparse Convolutions Spatially-sparse convolutional neural networks	2014	31
Transposed convolution Fully Convolutional Networks for Semantic Segmentation	2016	28
Masked Convolution Pixel Recurrent Neural Networks	2016	24
Selective Kernel Convolution Selective Kernel Networks	2019	21
CoordConv An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution	2018	15
(2+1)D Convolution A Closer Look at Spatiotemporal Convolutions for Action Recognition	2017	15
Spatially Separable Convolution	2000	12
MixConv MixConv: Mixed Depthwise Convolutional Kernels	2019	10
Octave Convolution Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution	2019	9
DynamicConv Pay Less Attention with Lightweight and Dynamic Convolutions	2019	9
PDC Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation	2022	9
Deformable Kernel Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation	2019	7
CondConv CondConv: Conditionally Parameterized Convolutions for Efficient Inference	2019	4
Depthwise Dilated Separable Convolution ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network	2018	4
Submanifold Convolution 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks	2017	4
Span-Based Dynamic Convolution ConvBERT: Improving BERT with Span-based Dynamic Convolution	2020	4
DCLS Dilated convolution with learnable spacings	2021	4
Active Convolution Active Convolution: Learning the Shape of Convolution for Image Classification	2017	3
Feature-Centric Voting Voting for Voting in Online Point Cloud Object Detection	2015	3
Attention-augmented Convolution Attention Augmented Convolutional Networks	2019	2
CKConv CKConv: Continuous Kernel Convolution For Sequential Data	2021	2
DAU-ConvNet Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks	2019	2
PP-OCR PP-OCR: A Practical Ultra Lightweight OCR System	2020	2
ShapeConv ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation	2021	2
DimConv DiCENet: Dimension-wise Convolutions for Efficient Networks	2019	1
LightConv Pay Less Attention with Lightweight and Dynamic Convolutions	2019	1
CP conv Hypercorrelation Squeeze for Few-Shot Segmentation	2021	1
Invertible NxN Convolution CInC Flow: Characterizable Invertible 3x3 Convolution	2021	1

Convolutions Edit

Methods Add a Method

Convolutions

Edit

Methods

Add a Method