JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search 文章

ArXiv CS.CV2026-05-27NEWSen作者: Dongyun Zou, Zhuoyang Zhang, Junyu Chen, Wenkun He, Qinhe Peng, Hanrong Ye, Yao Lu, Hongxu Yin, Yu Wang, Song Han, Han Cai
查看原文 →
关系图谱

JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search · 相关人物

暂无数据