1 code implementation • CVPR 2023 • Sheng Xu, Yanjing Li, Mingbao Lin, Peng Gao, Guodong Guo, Jinhu Lu, Baochang Zhang
At the upper level, we introduce a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy.
no code implementations • CVPR 2021 • Sheng Xu, Junhe Zhao, Jinhu Lu, Baochang Zhang, Shumin Han, David Doermann
At each layer, it exploits a differentiable binarization search (DBS) to minimize the angular error in a student-teacher framework.
no code implementations • 27 May 2021 • Xijun Li, Weilin Luo, Mingxuan Yuan, Jun Wang, Jiawen Lu, Jie Wang, Jinhu Lu, Jia Zeng
Our method is entirely data driven and thus adaptive, i. e., the relational representation of adjacent vehicles can be learned and corrected by ST-DDGN from data periodically.