no code implementations • CVPR 2022 • Xianing Chen, Qiong Cao, Yujie Zhong, Jing Zhang, Shenghua Gao, DaCheng Tao
Our DearKD is a two-stage framework that first distills the inductive biases from the early intermediate layers of a CNN and then gives the transformer full play by training without distillation.
no code implementations • 23 Sep 2021 • Xianing Chen, Chunlin Xu, Qiong Cao, Jialang Xu, Yujie Zhong, Jiale Xu, Zhengxin Li, Jingya Wang, Shenghua Gao
Transformers have shown preferable performance on many vision tasks.
no code implementations • CVPR 2021 • Zibo Zhao, Wen Liu, Yanyu Xu, Xianing Chen, Weixin Luo, Lei Jin, Bohui Zhu, Tong Liu, Binqiang Zhao, Shenghua Gao
One is a structure prior, it uses a human parsing map to represent the human body structure.