Training data-efficient image transformers & distillation through attention
Hugo Touvron 1 2 Matthieu Cord 1 2 Matthijs Douze 1
Francisco Massa 1 Alexandre Sablayrolles 1 Herve Jegou 1
Abstract
↑
Recently, neural networks purely based on atten-
tion were shown to address image understanding
tasks such as image classification. These high-
performing vi ...


雷达卡




京公网安备 11010802022788号







