RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

Xiaohan Ding(George Mason University), Guiguang Ding(Tsinghua University), Chunlong Xia(Baidu (China)), Jungong Han(Tsinghua University), Xiaojie Chu, Xiangyu Zhang(Northwestern Polytechnical University)
arXiv (Cornell University)
May 5, 2021
10.48550/arxiv.2105.01883
Cited by 65

Related Papers

RepVGG: Making VGG-style ConvNets Great Again
|Unknown|2021|2.5k
YOLOv10: Real-Time End-to-End Object Detection
|arXiv (Cornell University)|2024|1k
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
|Unknown|2019|828
Diverse Branch Block: Building a Convolution as an Inception-like Unit
|Unknown|2021|475
Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated Structure
|Unknown|2019|203