A-ViT: Adaptive Tokens for Efficient Vision Transformer 论文
20222022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)引用 293
Advanced Neural Network ApplicationsCCD and CMOS Imaging SensorsVisual Attention and Saliency Detection
A-ViT: Adaptive Tokens for Efficient Vision Transformer · 相关文章
暂无数据