Rethinking and Improving Relative Position Encoding for Vision Transformer
Kan Wu1,2,3, , Houwen Peng3,, , Minghao Chen3 , Jianlong Fu3 , Hongyang Chao1,2
1
School of Computer Science and Engineering, Sun Yat-sen University
2
The Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-sen University), Ministry of Education
3
Microsoft Research Asia
Abs ...


雷达卡




京公网安备 11010802022788号







