论文与标准
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
图像分块、位置嵌入与 Transformer 编码器的分类架构。
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby · 2021 · International Conference on Learning Representations 2021