Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	You, Haoran, Xiong, Yunyang, Dai, Xiaoliang, Wu, Bichen, Zhang, Peizhao, Fan, Haoqi, Vajda, Peter, Lin, Yingyan Celine
Format:	Preprint
Published:	2022
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2211.10526