1 code implementation • 18 Sep 2022 • Kang Chen, Shaochen Wang, Beihao Xia, Dongxu Li, Zhen Kan, Bin Li
We observe that the global characteristics of the transformer make it easier to extract contextual information to perform depth estimation of transparent areas.
1 code implementation • 15 Sep 2022 • Zhangli Zhou, Shaochen Wang, Ziyang Chen, Mingyu Cai, Zhen Kan
We demonstrate that using parallel branches as opposed to serial stacked convolutional layers will be a more powerful design for robotic visual grasping tasks.
1 code implementation • 24 Feb 2022 • Shaochen Wang, Zhangli Zhou, Zhen Kan
The first key design is that we adopt the local window attention to capture local contextual information and detailed features of graspable objects.
1 code implementation • 7 May 2021 • Yuan Pu, Shaochen Wang, Xin Yao, Bin Li
The performance of deep reinforcement learning methods prone to degenerate when applied to environments with non-stationary dynamics.
1 code implementation • 14 Apr 2021 • Yuan Pu, Shaochen Wang, Rui Yang, Xin Yao, Bin Li
Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks.
Ranked #1 on SMAC+ on Off_Superhard_parallel
no code implementations • 18 Apr 2020 • Xuejun Ma, Shaochen Wang, Wang Zhou
In this paper, we propose a new statistical inference method for massive data sets, which is very simple and efficient by combining divide-and-conquer method and empirical likelihood.