ResNet-D

2000년 도입 · 논문 10편에서 사용

ResNet-D is a modification on the ResNet architecture that utilises an average pooling tweak for downsampling. The motivation is that in the unmodified ResNet, the 1 × 1 convolution for the downsampling block ignores 3/4 of input feature maps, so this is modified so no information will be ignored

출처: Bag of Tricks for Image Classification with Convolutional Neural Networks

소개 논문: Bag of Tricks for Image Classification with Convolutional Neural Networks