RepVGG

2000년 도입 · 논문 13편에서 사용

RepVGG is a VGG-style convolutional architecture. It has the following advantages: - The model has a VGG-like plain (a.k.a. feed-forward) topology 1 without any branches. I.e., every layer takes the output of its only preceding layer as input and feeds the output into its only following layer. - The model’s body uses only 3 × 3 conv and ReLU. - The concrete architecture (including the specific depth and layer widths) is instantiated with no automatic search, manual refinement, compound scaling, nor other heavy designs.

출처: RepVGG: Making VGG-style ConvNets Great Again

소개 논문: RepVGG: Making VGG-style ConvNets Great Again