SPViT: Enabling Faster Vision Transformers via Soft Token Pruning

@Article{Kong2021SPViTEF,
 author = {Zhenglun Kong and Peiyan Dong and Xiaolong Ma and Xin Meng and Wei Niu and Mengshu Sun and Bin Ren and Minghai Qin and H. Tang and Yanzhi Wang},
 booktitle = {European Conference on Computer Vision},
 pages = {620-640},
 title = {SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning},
 year = {2021}
}