Xiaoning Pi

Xiaoning Pi

Auto-generated profile, based on publicly available information

Xiaoning Pi

School of Computer and Communication Engineering, University of Science and Technology Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
15 October 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YXYulai Xie
Yulai Xie
XPXiaoning Pi
Xiaoning Pi
YZYang Zhang
Yang Zhang
FRFang Ren
Fang Ren

16 June 2023
Verified
Conference Paper
Open access
XWXiaohui Wang
Xiaohui Wang
YXYulai Xie
Yulai Xie
YZYang Zhang
Yang Zhang
XPXiaoning Pi
Xiaoning Pi
FRFang Ren
Fang Ren

20 May 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
FRFang Ren
Fang Ren
YXYulai Xie
Yulai Xie
XPXiaoning Pi
Xiaoning Pi

21 June 2024
Verified
Conference Paper
Open access
XPXiaoNing Pi
XiaoNing Pi
YXYuLai Xie
YuLai Xie
YZYang Zhang
Yang Zhang
XWXiaoHui Wang
XiaoHui Wang
FRFang Ren
Fang Ren
In industrial production, visual defect inspection is crucial for ensuring product quality. However, due to difficulties in sample collection during defect inspection, there is often a scarcity of diverse defective samples, leading most data generation methods to fail in generating high-diversity data. Therefore, this paper proposes the Automatic Iterative Diversity Improvement training strategy to improve the diversity of generated data with only a few training samples, which can improve the performance and generalization of downstream tasks. During the training process, given the characteristics of visual defects, we design the Defect Diversity-based Picking and Evaluation to pick up diverse samples and assess the diversity regarding defect location and shape. Experiments show that the method can generate high-diversity defect samples with high quality for industrial defect scenarios even in zero-shot learning tasks. The effectiveness of the generated data is also verified by the down-streaming defect detection task.