Image Feature Extractors

Edit

Computer Vision • 63 methods

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.

Subcategories

1 Convolutions

Methods

Add a Method

Method	Year	Papers
Convolution	1980	19146
1x1 Convolution Network In Network	2013	5557
Depthwise Convolution	2016	1283
Pointwise Convolution	2016	1270
Depthwise Separable Convolution Xception: Deep Learning With Depthwise Separable Convolutions	2017	1143
Dilated Convolution Multi-Scale Context Aggregation by Dilated Convolutions	2015	669
Grouped Convolution ImageNet Classification with Deep Convolutional Neural Networks	2012	569
3D Convolution	2015	205
Non-Local Operation Non-local Neural Networks	2017	181
SAC DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution	2020	162
Deformable Convolution Deformable Convolutional Networks	2017	147
1D CNN Convolutional Neural Network and Rule-Based Algorithms for Classifying 12-lead ECGs	2020	90
Invertible 1x1 Convolution Glow: Generative Flow with Invertible 1x1 Convolutions	2018	76
Groupwise Point Convolution ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network	2018	53
Sparse Convolutions Spatially-sparse convolutional neural networks	2014	36
Transposed convolution Fully Convolutional Networks for Semantic Segmentation	2016	29
Selective Kernel Convolution Selective Kernel Networks	2019	28
Masked Convolution Pixel Recurrent Neural Networks	2016	26
(2+1)D Convolution A Closer Look at Spatiotemporal Convolutions for Action Recognition	2017	17
CoordConv An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution	2018	16
PDC Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation	2022	13
Spatially Separable Convolution	2000	12
MixConv MixConv: Mixed Depthwise Convolutional Kernels	2019	12
DynamicConv Pay Less Attention with Lightweight and Dynamic Convolutions	2019	10
Octave Convolution Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution	2019	9
Deformable Kernel Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation	2019	8
DCLS Dilated convolution with learnable spacings	2021	6
Submanifold Convolution 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks	2017	6
Large Kernel Size ImageNet Classification with Deep Convolutional Neural Networks	2012	6
CondConv CondConv: Conditionally Parameterized Convolutions for Efficient Inference	2019	5
Involution Involution: Inverting the Inherence of Convolution for Visual Recognition	2021	5
Span-Based Dynamic Convolution ConvBERT: Improving BERT with Span-based Dynamic Convolution	2020	5
Feature-Centric Voting Voting for Voting in Online Point Cloud Object Detection	2015	4
Depthwise Dilated Separable Convolution ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network	2018	4
PP-OCR PP-OCR: A Practical Ultra Lightweight OCR System	2020	4
Attention-augmented Convolution Attention Augmented Convolutional Networks	2019	3
Active Convolution Active Convolution: Learning the Shape of Convolution for Image Classification	2017	3
Local Relation Layer Local Relation Networks for Image Recognition	2019	3
CKConv CKConv: Continuous Kernel Convolution For Sequential Data	2021	2
ShapeConv ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation	2021	2
DAU-ConvNet Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks	2019	2
PushPull-Conv PushPull-Net: Inhibition-driven ResNet robust to image corruptions	2024	1
CP conv Hypercorrelation Squeeze for Few-Shot Segmentation	2021	1
DimConv DiCENet: Dimension-wise Convolutions for Efficient Networks	2019	1
LightConv Pay Less Attention with Lightweight and Dynamic Convolutions	2019	1
Hamburger Is Attention Better Than Matrix Decomposition?	2021	1
Invertible NxN Convolution CInC Flow: Characterizable Invertible 3x3 Convolution	2021	1

Image Feature Extractors Edit

Methods Add a Method

Image Feature Extractors

Edit

Methods

Add a Method