Incorporating Convolution Designs into Visual Transformers

CeiT：将卷积设计整合到视觉Transformers中.

CvT: Introducing Convolutions to Vision Transformers

CvT：向视觉Transformer中引入卷积.

Per-Pixel Classification is Not All You Need for Semantic Segmentation

MaskFormer：逐像素分类并不是语义分割所必需的.

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

PVT：一种无卷积密集预测的通用骨干.

Segmenter: Transformer for Semantic Segmentation

Segmenter：为语义分割设计的视觉Transformer.

Rethinking Spatial Dimensions of Vision Transformers

PiT：重新思考视觉Transformer的空间维度.