要阅读的论文列表

要读的论文

后面标记是否读完或者不读了

1. AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE
   【已完成】笔记：2022.11.18

2. CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
   【已完成】笔记：2022.11.19

3. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

4. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

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

6. Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

7. Multiscale Vision Transformers

8. Scaling Vision Transformers

9. Rethinking Spatial Dimensions of Vision Transformers

10. DeepViT: Towards Deeper Vision Transformer

11. Conditional Positional Encodings for Vision Transformers