3 papers
cs.LG2025
Deep Neural Networks Inspired by Differential Equations
Yongshuai Liu, Lianfang Wang, Kuilin Qin +6
Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, ne…
cs.CV2025
Contour Field based Elliptical Shape Prior for the Segment Anything Model
Xinyu Zhao, Faqiang Wang, Li Cui +2
The elliptical shape prior information plays a vital role in improving the accuracy of image segmentation for specific tasks in medical and natural images. Existing deep learning-b…
math.OC2024
An inexact Bregman proximal point method and its acceleration version for unbalanced optimal transport
Xiang Chen, Faqiang Wang, Jun Liu +1
The Unbalanced Optimal Transport (UOT) problem plays increasingly important roles in computational biology, computational imaging and deep learning. Scaling algorithm is widely use…