Zobrazeno 1 - 10
of 90
pro vyhledávání: '"Zeng, Liaoyuan"'
We consider the problem of minimizing a convex separable objective (as a separable sum of two proper closed convex functions $f$ and $g$) over a linear coupling constraint. We assume that $f$ can be decomposed as the sum of a smooth part having H\"ol
Externí odkaz:
http://arxiv.org/abs/2409.14957
Autor:
Agyemang, Isaac Osei, Chen, Jianwen, Zeng, Liaoyuan, Adjei-Mensah, Isaac, Acheampong, Daniel, Boateng, Gordon Owusu, Baffour, Adu Asare
Image environments and noisy labels hinder deep learning-based inference models in structural damage detection. Post-detection, there is the challenge of reliance on manual assessments of detected damages. As a result, Guided-DetNet, characterized by
Externí odkaz:
http://arxiv.org/abs/2407.19694
Autor:
Cui, Weiwei, Wang, Yaqi, Li, Yilong, Song, Dan, Zuo, Xingyong, Wang, Jiaojiao, Zhang, Yifan, Zhou, Huiyu, Chong, Bung san, Zeng, Liaoyuan, Zhang, Qianni
Accurate tooth volume segmentation is a prerequisite for computer-aided dental analysis. Deep learning-based tooth segmentation methods have achieved satisfying performances but require a large quantity of tooth data with ground truth. The dental dat
Externí odkaz:
http://arxiv.org/abs/2208.01643
Autor:
Cui, Weiwei, Wang, Yaqi, Zhang, Qianni, Zhou, Huiyu, Song, Dan, Zuo, Xingyong, Jia, Gangyong, Zeng, Liaoyuan
3D tooth segmentation is a prerequisite for computer-aided dental diagnosis and treatment. However, segmenting all tooth regions manually is subjective and time-consuming. Recently, deep learning-based segmentation methods produce convincing results
Externí odkaz:
http://arxiv.org/abs/2206.08778
The Frank-Wolfe (FW) method, which implements efficient linear oracles that minimize linear approximations of the objective function over a fixed compact convex set, has recently received much attention in the optimization and machine learning litera
Externí odkaz:
http://arxiv.org/abs/2112.14404
Autor:
Zeng, Liaoyuan, Pong, Ting Kei
Trust-region (TR) type method, based on a quadratic model such as the trust-region subproblem (TRS) and $ p $-regularization subproblem ($p$RS), is arguably one of the most successful methods for unconstrained minimization. In this paper, we study a
Externí odkaz:
http://arxiv.org/abs/2109.01829
Publikováno v:
In Engineering Applications of Artificial Intelligence July 2024 133 Part E
Recently, in a series of papers [32,38,39,41], the ratio of $\ell_1$ and $\ell_2$ norms was proposed as a sparsity inducing function for noiseless compressed sensing. In this paper, we further study properties of such model in the noiseless setting,
Externí odkaz:
http://arxiv.org/abs/2007.12821
The split feasibility problem is to find an element in the intersection of a closed set $C$ and the linear preimage of another closed set $D$, assuming the projections onto $C$ and $D$ are easy to compute. This class of problems arises naturally in m
Externí odkaz:
http://arxiv.org/abs/1903.01101
Autor:
Zeng, Liaoyuan1 (AUTHOR), Zhang, Yongle2 (AUTHOR) yongle-zhang@163.com, Li, Guoyin3 (AUTHOR), Pong, Ting Kei4 (AUTHOR), Wang, Xiaozhou4 (AUTHOR)
Publikováno v:
Mathematical Programming. Nov2024, Vol. 208 Issue 1/2, p717-761. 45p.