Y
Yuxuan Zhang
Researcher at Beihang University
Publications - 4
Citations - 93
Yuxuan Zhang is an academic researcher from Beihang University. The author has contributed to research in topics: Image segmentation & Similarity measure. The author has an hindex of 2, co-authored 3 publications receiving 44 citations.
Papers
More filters
Journal ArticleDOI
Similarity Measure-Based Possibilistic FCM With Label Information for Brain MRI Segmentation
TL;DR: An improved possibilistic fuzzy fuzzy means (FCM) method based on a similarity measure is proposed to improve the segmentation performance for MRI brain images, providing mitigation to the cluster-size problem, resistance to noisy images, and applicability to data with more complex distribution.
Journal ArticleDOI
Intuitionistic Center-Free FCM Clustering for MR Brain Image Segmentation
TL;DR: An intuitionistic center-free fuzzy c-means clustering method for magnetic resonance (MR) brain image segmentation that could outperform several fuzzy-clustering-based methods and could achieve comparable results to the standard published methods like statistical parametric mapping and FMRIB automated segmentation tool.
Journal ArticleDOI
Multiple-Surface-Approximation-Based FCM With Interval Memberships for Bias Correction and Segmentation of Brain MRI
TL;DR: A novel multiple-surface-approximation-based FCM with interval membership method for simultaneous bias correction and segmentation of Brain MRI that is less sensitive to noise by introducing effects of neighboring pixels and obtains better results of both bias field correction and segmentsation than comparing methods.
Proceedings ArticleDOI
BSOLO: Boundary-Aware One-Stage Instance Segmentation SOLO
Yuxuan Zhang,Wei Yang +1 more
TL;DR: This paper proposes a boundary-aware method to refine boundary information, called BSOLO, to design a Hungarian-Algorithm-based boundary loss to calculate matching costs between boundaries and introduces a Prototype Attention Module (PAM) for mask assembling through channel attention, which enhances informative features and spotlights important prototypes.