Shumin Ding

Shumin Ding

Auto-generated profile, based on publicly available information

Shumin Ding

School of Information and Communication Engineering, Zhongyuan University of Technology, Zhengzhou 451191, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
17 March 2026 in Electronics
Verified
Journal Article
Open access
PDF file
ZLZhoufeng Liu
Zhoufeng Liu
QHQihang He
Qihang He
CLChunlei Li
Chunlei Li
SDShumin Ding
Shumin Ding
JWJunpu Wang
Junpu Wang
XSXinnan Shao
Xinnan Shao
Few-shot object detection suffers from limited annotations, redundant background interference, insufficient feature interaction, and severe sample imbalance. Existing meta-learning-based methods extract class prototypes from support images but often fail to effectively suppress background noise or align channel-wise features between support and query branches. To address these issues, we propose a few-shot object detection method based on background reconstruction and multi-channel interactive feature fusion. First, a background reconstruction module is designed to suppress redundant background interference by applying random region masking to support set images, thereby generating robust class prototype features that are resistant to background noise. Second, a multi-channel interactive feature fusion module is designed, which leverages depthwise separable convolution to enable effective channel-wise feature interaction and information alignment between support class prototypes and query features, thereby enhancing cross-branch feature interaction and fusion. Finally, to address the uneven sample distribution and the foreground–background imbalance in few-shot scenarios, we proposed a category-aware weighted loss. By appropriately weighting the contributions of different object categories and background samples, the proposed loss encourages balanced optimization, resulting in faster convergence and improved detection performance. Experimental results demonstrate that the proposed method improves detection accuracy and generalization performance under few-shot settings. On the Pascal VOC dataset (Split1), the proposed method achieves 45.1%, 62.9%, and 67.1% under 1-shot, 3-shot, and 10-shot settings, respectively, outperforming the baseline; consistent improvements are also observed on the MS COCO dataset and the DIOR dataset.

15 October 2026 in Pattern Analysis and Applications
Verified
Journal Article
Closed access
PDF file
ZLZhoufeng Liu
Zhoufeng Liu
YHYi Huangfu
Yi Huangfu
SDShumin Ding
Shumin Ding
JWJunpu Wang
Junpu Wang
CLChunlei Li
Chunlei Li
YMYongLi Ma
YongLi Ma