no code implementations • 25 Apr 2024 • Shi-Yu Xia, Wenxuan Zhu, Xu Yang, Xin Geng
When initializing variable-sized models adapting for different resource constraints, SWS achieves better results while reducing around 20x parameters stored to initialize these models and around 10x pre-training costs, in contrast to the pre-training and fine-tuning approach.
no code implementations • 18 Mar 2023 • Jianye Yi, Xiaopin Zhong, Weixiang Liu, Wenxuan Zhu, Zongze Wu, Yuanlong Deng
Therefore, we propose an abstract and universal edge supervision method called Edge-aware Plug-and-play Scheme (EPS), which can be easily and quickly applied to any semantic segmentation models.
no code implementations • 28 Nov 2022 • Wenxuan Zhu, Chao Yu, Qiang Zhang
Offline reinforcement learning promises to alleviate this issue by exploiting the vast amount of observational data available in the real world.
no code implementations • 10 Nov 2018 • Chao Yu, Tianpei Yang, Wenxuan Zhu, Dongxu Wang, Guangliang Li
Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning.