Vit和Mamba论文学习

1. ICCV2021: CvT: Introducing Convolutions to Vision Transformers
2. CVPRA2022 AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
3. CVPR2024 Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers