Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

用Transformer从序列到序列的角度重新思考语义分割.

CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

CrossViT：图像分类的交叉注意力多尺度视觉Transformer.

Do We Really Need Explicit Position Encodings for Vision Transformers?

视觉Transformer真的需要显式位置编码吗？

Visual Transformers: Token-based Image Representation and Processing for Computer Vision

VT：基于Token的图像表示和处理.

LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference

LeViT：以卷积网络的形式进行快速推理的视觉Transformer.

Escaping the Big Data Paradigm with Compact Transformers

CCT：使用紧凑的Transformer避免大数据依赖.