Yiming Du
Papers
1
Total Citations
9
H-Index
1
About
Yiming Du is a researcher whose work centers on object detection and the critical role of data distribution in computer vision performance. In their highly regarded 2021 survey, "A Survey on Object Detection Performance with Different Data Distributions," Du systematically analyzed how variations in training data—such as class imbalance, domain shifts, and dataset biases—affect the accuracy and robustness of detection models. This contribution, which has garnered 9 citations, provides a foundational reference for researchers seeking to design more reliable vision systems in real-world scenarios where data is rarely uniform. By synthesizing diverse experimental findings, Du offers practical insights into model generalization and dataset curation, making their work valuable for both academic study and applied engineering. Their focus on bridging the gap between controlled benchmarks and messy, real-world data highlights a commitment to advancing practical computer vision. For students and researchers exploring object detection or data-centric AI, Du’s survey serves as a clear, concise roadmap to understanding one of the field’s most persistent challenges.
Research Focus
Key Achievements
Top Papers
- 1