RepVGG: Making VGG-style ConvNets Great Again

Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, Jian Sun

Type: Preprint

Publication Date: 2021-01-01

Citations: 19

DOI: https://doi.org/10.48550/arxiv.2101.03697

View Publication

Locations

arXiv (Cornell University) - View - PDF
Aberystwyth Research portal (Aberystwyth University) - View - PDF
DataCite API - View

Similar Works

Action	Title	Year	Authors
+ PDF Chat	RepVGG: Making VGG-style ConvNets Great Again	2021	Xiaohan Ding Xiangyu Zhang Ningning Ma Jungong Han Guiguang Ding Jian Sun
+	RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets	2023	Zhicheng Cai Xiaohan Ding Qiu Shen Xun Cao
+	EfficientNetV2: Smaller Models and Faster Training	2021	Mingxing Tan Quoc V. Le
+	Diverse Branch Block: Building a Convolution as an Inception-like Unit	2021	Xiaohan Ding Xiangyu Zhang Jungong Han Guiguang Ding
+ PDF Chat	DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs	2024	Donghyun Kim Byeongho Heo Dongyoon Han
+	Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training	2021	Dominic Masters Antoine Labatie Zach Eaton-Rosen Carlo Luschi
+	Lets keep it simple: using simple architectures to outperform deeper architectures.	2016	Seyyed Hossein Hasanpour Mohammad Rouhani Javad Vahidi Reza Saadati
+	CoAtNet: Marrying Convolution and Attention for All Data Sizes	2021	Zihang Dai Hanxiao Liu Quoc V. Le Mingxing Tan
+	Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures	2016	Seyyed Hossein Hasanpour Mohammad Rouhani Mohsen Fayyaz Mohammad Sabokrou
+	CoAtNet: Marrying Convolution and Attention for All Data Sizes	2021	Zihang Dai Hanxiao Liu Quoc V. Le Mingxing Tan
+	EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design	2023	Kaiheng Weng Xiangxiang Chu XU Xiao-ming Junshi Huang Xiaoming Wei
+	Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures.	2016	Seyyed Hossein Hasanpour Mohammad Rouhani Mohsen Fayyaz Mohammad Sabokrou
+	Memory-Efficient Implementation of DenseNets	2017	Geoff Pleiss Danlu Chen Gao Huang Tongcheng Li Laurens van der Maaten Kilian Q. Weinberger
+	Memory-Efficient Implementation of DenseNets	2017	Geoff Pleiss Danlu Chen Gao Huang Tongcheng Li Laurens van der Maaten Kilian Q. Weinberger
+	EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks	2019	Mingxing Tan Quoc V. Le
+	TResNet: High Performance GPU-Dedicated Architecture	2020	Tal Ridnik Hussam Lawen Asaf Noy Emanuel Ben Baruch Gilad Sharir Itamar Friedman
+	InceptionNeXt: When Inception Meets ConvNeXt	2023	Weihao Yu Pan Zhou Shuicheng Yan Xinchao Wang
+	TResNet: High Performance GPU-Dedicated Architecture	2020	Tal Ridnik Hussam Lawen Asaf Noy Emanuel Ben Baruch Gilad Sharir Itamar Friedman
+	Efficient CNN Architecture Design Guided by Visualization	2022	Liangqi Zhang Haibo Shen Yihao Luo Xiang Cao Leixilan Pan Tianjiang Wang Feng Qi
+ PDF Chat	Designing Concise ConvNets with Columnar Stages	2024	Ashish Kumar Jaesik Park

Works That Cite This (8)

Action	Title	Year	Authors
+	Unrestricted Adversarial Attacks on ImageNet Competition	2021	Yuefeng Chen Xiaofeng Mao Yuan He Hui Xue Chao Li Yinpeng Dong Qian Fu Xiao Yang Wenzhao Xiang Tianyu Pang
+	Fast query-by-example speech search using separable model	2021	Yuguang Yang Yu Pan Xin Dong Minqiang Xu
+	Non-deep Networks	2021	Ankit Goyal Alexey Bochkovskiy Jia Deng Vladlen Koltun
+ PDF Chat	Improving Object Detection by Label Assignment Distillation	2022	Chuong Hoang Nguyen Thuy C. Nguyen Tuan N. Tang Nam L. H. Phan
+	RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition	2021	Xiaohan Ding Chunlong Xia Xiangyu Zhang Xiaojie Chu Jungong Han Guiguang Ding
+	Sparse PointPillars: Exploiting Sparsity in Birds-Eye-View Object Detection.	2021	Kyle Vedder Eric Eaton
+	Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report	2021	Andrey Ignatov Radu Timofte Maurizio Denna Abdel Younes Andrew Lek Mustafa Ayazoğlu Jie Liu Zongcai Du Jiaming Guo Xueyi Zhou
+	Layer Folding: Neural Network Depth Reduction using Activation Linearization	2021	Amir Ben Dror Niv Zehngut Avraham Raviv E. Artyomov Ran Vitek Roy J. Jevnisek

Works Cited by This (35)

Action	Title	Year	Authors
+	cuDNN: Efficient Primitives for Deep Learning	2014	Sharan Chetlur Cliff Woolley Philippe Vandermersch Jonathan Cohen John Tran Bryan Catanzaro Evan Shelhamer
+	Very Deep Convolutional Networks for Large-Scale Image Recognition	2014	Karen Simonyan Andrew Zisserman
+	Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift	2015	Sergey Ioffe Christian Szegedy
+ PDF Chat	Going deeper with convolutions	2015	Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke Andrew Rabinovich
+ PDF Chat	Fast Algorithms for Convolutional Neural Networks	2016	Andrew Lavin Scott Gray
+ PDF Chat	Rethinking the Inception Architecture for Computer Vision	2016	Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jon Shlens Zbigniew Wojna
+ PDF Chat	Deep Residual Learning for Image Recognition	2016	Kaiming He Xiangyu Zhang Shaoqing Ren Jian Sun
+ PDF Chat	The Cityscapes Dataset for Semantic Urban Scene Understanding	2016	Marius Cordts Mohamed Omran Sebastian Ramos Timo Rehfeld Markus Enzweiler Rodrigo Benenson Uwe Franke Stefan Roth Bernt Schiele
+	Pruning Filters for Efficient ConvNets	2016	Hao Li Asim Kadav Igor Đurđanović Hanan Samet Hans Peter Graf
+ PDF Chat	Xception: Deep Learning with Depthwise Separable Convolutions	2017	François Chollet