activity
20132023
most citedAccurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

1k citations · 2.3k across the 46 of their papers we have counts for

collaborators
Showing 2022Show all

7 papers · 1 filter

math.NA2022★ 5 cited

DOSnet as a Non-Black-Box PDE Solver: When Deep Learning Meets Operator Splitting

Yuan Lan, Zhen Li, Jie Sun +1

Deep neural networks (DNNs) recently emerged as a promising tool for analyzing and solving complex differential equations arising in science and engineering applications. Alternati…

cs.CV2022

BoxPolyp:Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations

Jun Wei, Yiwen Hu, Guanbin Li +3

Accurate polyp segmentation is of great importance for colorectal cancer diagnosis and treatment. However, due to the high cost of producing accurate mask annotations, existing pol…

cs.CV2022★ 29 cited

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

Ziyi Zhang, Weikai Chen, Hui Cheng +4

We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to…

cs.CV2022★ 15 cited

Designing An Illumination-Aware Network for Deep Image Relighting

Zuo-Liang Zhu, Zhen Li, Rui-Xun Zhang +2

Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images. Creating or finding satisfying lighting conditions, in re…

eess.SY2022

Barrier Certified Safety Learning Control: When Sum-of-Square Programming Meets Reinforcement Learning

Hejun Huang, Zhenglong Li, Dongkun Han

Safety guarantee is essential in many engineering implementations. Reinforcement learning provides a useful way to strengthen safety. However, reinforcement learning algorithms can…

cs.LG2022★ 1 cited

Contextual Bandits with Knapsacks for a Conversion Model

Zhen Li, Gilles Stoltz

We consider contextual bandits with knapsacks, with an underlying structure between rewards generated and cost vectors suffered. We do so motivated by sales with commercial discoun…

eess.IV2022★ 10 cited

Towards An End-to-End Framework for Flow-Guided Video Inpainting

Zhen Li, Cheng-Ze Lu, Jianhua Qin +2

Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories. However, the hand-…