Zhaoyang Wei

Zhaoyang Wei

Auto-generated profile, based on publicly available information

Zhaoyang Wei

University of the Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 October 2025
Verified
Conference Paper
Open access
CQChenhui Qiang
Chenhui Qiang
ZWZhaoyang Wei
Zhaoyang Wei
XHXumeng Han
Xumeng Han
ZWZipeng Wang
Zipeng Wang
SLSiyao Li
Siyao Li
ZHZhenjun Han
Zhenjun Han

1 July 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ZWZhaoyang Wei
Zhaoyang Wei
XHXumeng Han
Xumeng Han
XYXuehui Yu
Xuehui Yu
XYXue Yang
Xue Yang
GLGuorong Li
Guorong Li
JJJianbin Jiao
Jianbin Jiao
Single-point annotation is increasingly prominent in visual tasks for labeling cost reduction. However, it challenges tasks requiring high precision, such as the point-prompted instance segmentation (PPIS) task, which aims to estimate precise masks using single-point prompts to train a segmentation network. Due to the constraints of point annotations, granularity ambiguity and boundary uncertainty arise i.e., the difficulty distinguishing between different levels of detail (e.g., whole object vs. parts) and the challenge of precisely delineating object boundaries. Previous works have usually inherited the paradigm of mask generation along with proposal selection to achieve PPIS. However, proposal selection relies solely on category information, failing to resolve the ambiguity of different granularity. Furthermore, mask generators offer only finite discrete solutions that often deviate from actual masks, particularly at boundaries. To address these issues, we propose the Semantic-Aware Point-Prompted Instance Segmentation Network (SAPNet). It integrates Point Distance Guidance and Box Mining Strategy to tackle group and local issues caused by the point's granularity ambiguity. Additionally, we incorporate completeness scores within proposals to add spatial granularity awareness, enhancing multiple instance learning (MIL) in proposal selection termed S-MIL. The Multi-level Affinity Refinement conveys pixel and semantic clues, narrowing boundary uncertainty during mask refinement. These modules culminate in SAPNet++, mitigating point prompt's granularity ambiguity and boundary uncertainty and significantly improving segmentation performance. Extensive experiments on four challenging datasets validate the effectiveness of our methods, highlighting the potential to advance PPIS.

1 October 2026
Verified
Book Chapter
Closed access
PDF file
ZWZhaoyang Wei
Zhaoyang Wei
ZWZipeng Wang
Zipeng Wang
YCYushe Cao
Yushe Cao
CQChenhui Qiang
Chenhui Qiang
SCShuaibing Cheng
Shuaibing Cheng
ZHZhenjun Han
Zhenjun Han

9 November 2026
Verified
Conference Paper
Open access
ZWZhaoyang Wei
Zhaoyang Wei
WDWenchao Ding
Wenchao Ding
CQChenhui Qiang
Chenhui Qiang
SNSen Nie
Sen Nie
SLShiyin Lin
Shiyin Lin
ZWZheng Wei
Zheng Wei

28 August 2026 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ZWZhaoyang Wei
Zhaoyang Wei
BJBowen Jiang
Bowen Jiang
XHXumeng Han
Xumeng Han
JLJiashu Li
Jiashu Li
XYXuehui Yu
Xuehui Yu
JJJianbin Jiao
Jianbin Jiao