YOLO-DSNet for Small Target Detection

RAIDS Lab Authors

Zhengyi Yang

Director

Details

Research Area

Tags

Resources

Abstract

Small target detection in Unmanned Aerial Vehicle (UAV) applications is often plagued by inherent challenges such as small object sizes, sparse information, and complex background interference. Traditional detection algorithms and existing YOLO series models suffer from limitations in detection accuracy and fine-grained detail preservation. To address this, this paper proposes YOLO-DSNet, a small target detection network based on YOLOv13n. First, we introduce the dual-stream attention module (DSAM), which enhances discriminative features by leveraging bidirectional context modeling. Second, we design the Multi-scale Attention C2f (MSA-C2f) module - an adaptive architecture that optimizes feature extraction via multi-scale enhancement, effectively preserving and integrating small target information. Finally, through dataset augmentation, we significantly improve the mode's detection performance. The proposed YOLO-DSNet achieves a mAP@0.5 improvement from 30.8% to 40.1% on the VisDrone2019 dataset with only 0.8 million additional parameters, yielding a 30% accuracy gain while increasing computational overhead by merely 11.6 Gigaflops (GFLOPs). Experiments demonstrate YOLO-DSNet's effectiveness in small target detection tasks such as UAV aerial photography and remote sensing imagery, successfully balancing accuracy and efficiency with high practical value.

Author Affiliations

@article{xu2026yolodsnet,
  title = {YOLO-DSNet for Small Target Detection},
  author = {Xu, Haokun and He, Huangleshuai and Zhi, Qike and Yang, Zhengyi and Han, Bocheng},
  volume = {16},
  issn = {2076-3417},
  url = {http://dx.doi.org/10.3390/app16031493},
  doi = {10.3390/app16031493},
  number = {3},
  journal = {Applied Sciences},
  publisher = {MDPI AG},
  year = {2026},
  month = Feb,
  pages = {1493}
}