论文与标准

A ConvNet for the 2020s

左侧使用瓶颈卷积，右侧使用深度卷积和通道扩展。图中数值表示各模块的通道数。

Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie · 2022 · IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022