1 code implementation • 12 Oct 2023 • Runxue Bao, Yiming Sun, Yuhe Gao, Jindong Wang, Qiang Yang, Haifeng Chen, Zhi-Hong Mao, Ye Ye
These methods typically presuppose identical feature spaces and label spaces in both domains, known as homogeneous transfer learning, which, however, is not always a practical assumption.
no code implementations • 17 Aug 2022 • Jason Xiaotian Dou, Alvin Qingkai Pan, Runxue Bao, Haiyi Harry Mao, Lei Luo, Zhi-Hong Mao
Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation.
no code implementations • 18 Dec 2020 • Zhengeng Yang, Hongshan Yu, Yong He, Zhi-Hong Mao, Ajmal Mian
By learning to solve a Jigsaw Puzzle problem with 25 patches and transferring the learned features to semantic segmentation task on Cityscapes dataset, we achieve a 5. 8 percentage point improvement over the baseline model that initialized from random values.
no code implementations • 16 Mar 2019 • Zhengeng Yang, Hongshan Yu, Qiang Fu, Wei Sun, Wenyan Jia, Mingui Sun, Zhi-Hong Mao
The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding.