EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Student Network with Dynamic Multi-Teacher Distillation for Optical Remote Sensing Object Detection

Jiarui Cai, Xudong Su, Haojun Deng, Jun Deng

Sensors · 20.07.2026 · 26 (14) · 4599

DOI: 10.3390/s26144599 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.07.2026. Verfasst von Jiarui Cai und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Engineering, Xidian University, North Campus: No. 2 South Taibai Road, Xi'an 710071, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Optical remote sensing object detection faces challenges such as large variations in scale, slender and direction-sensitive targets, complex backgrounds, and limited deployment resources. This paper proposes a lightweight geometrically decoupled student network with a dynamic multi-teacher distillation framework. Based on YOLO11n, the student detector keeps the original classification branch while redesigning the regression branches at different scales. Lightweight regression towers are used for the shallow and deep branches, whereas a geometrically decoupled regression tower is introduced only at the intermediate branch to enhance localization for slender and orientation-sensitive objects with limited extra cost. A geometry-adaptive box loss is further employed to stabilize localization training. For knowledge transfer, three specialized teachers are constructed for semantic classification, geometric regression, and structural topology supervision. A branch-decoupled adaptive weighting strategy dynamically integrates their complementary knowledge for classification and regression distillation. Experiments on DIOR show that the proposed model reduces parameters by 6.8% and GFLOPs by 13.9%, while improving mAP50 by 0.23 percentage points over YOLO11n. Validation on NWPU VHR-10 and deployment tests using PT, ONNX, and TensorRT further demonstrate improved accuracy–efficiency trade-offs and practical inference acceleration.

Schlagwörter

Stichwörter der Autor:innen

YOLO11dynamic teacher weightinggeometrically decoupled regression towerlightweight object detectionmulti-teacher knowledge distillationoptical remote sensing object detection

Autor:innen und Institutionen

  • School of Electronic Engineering, Xidian University, North Campus: No. 2 South Taibai Road, Xi'an 710071, China.

Zitieren

APA

Cai, J., Su, X., Deng, H., & Deng, J. (2026). A Lightweight Student Network with Dynamic Multi-Teacher Distillation for Optical Remote Sensing Object Detection. Sensors, 26(14), 4599. https://doi.org/10.3390/s26144599

Vancouver

Cai J, Su X, Deng H, Deng J. A Lightweight Student Network with Dynamic Multi-Teacher Distillation for Optical Remote Sensing Object Detection. Sensors. 2026;26(14):4599. doi:10.3390/s26144599

BibTeX
@article{Cai2026,
  author = {Cai, Jiarui and Su, Xudong and Deng, Haojun and Deng, Jun},
  title = {A Lightweight Student Network with Dynamic Multi-Teacher Distillation for Optical Remote Sensing Object Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4599},
  doi = {10.3390/s26144599}
}
Kostenlos starten →