Please add our CVPR2023 paper to Backbone and Vision Transformer
changsn opened this issue · 1 comments
changsn commented
Hi,
Please add our CVPR2023 paper to Backbone and Vision Transformer.
Name: Making Vision Transformers Efficient from A Token Sparsification View
Link: https://arxiv.org/abs/2303.08685
Code: https://github.com/changsn/STViT-R
Thank you!
amusi commented
Now the project has been added, thanks for sharing.