首页|A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

扫码查看
原文链接
  • 万方数据
  • 维普
Unmanned aerial vehicles(UAVs)have gained sig-nificant attention in practical applications,especially the low-alti-tude aerial(LAA)object detection imposes stringent require-ments on recognition accuracy and computational resources.In this paper,the LAA images-oriented tensor decomposition and knowledge distillation-based network(TDKD-Net)is proposed,where the TT-format TD(tensor decomposition)and equal-weighted response-based KD(knowledge distillation)methods are designed to minimize redundant parameters while ensuring com-parable performance.Moreover,some robust network structures are developed,including the small object detection head and the dual-domain attention mechanism,which enable the model to leverage the learned knowledge from small-scale targets and selectively focus on salient features.Considering the imbalance of bounding box regression samples and the inaccuracy of regres-sion geometric factors,the focal and efficient IoU(intersection of union)loss with optimal transport assignment(F-EIoU-OTA)mechanism is proposed to improve the detection accuracy.The proposed TDKD-Net is comprehensively evaluated through extensive experiments,and the results have demonstrated the effectiveness and superiority of the developed methods in com-parison to other advanced detection algorithms,which also present high generalization and strong robustness.As a resource-efficient precise network,the complex detection of small and occluded LAA objects is also well addressed by TDKD-Net,which provides useful insights on handling imbalanced issues and real-izing domain adaptation.

Attention mechanismknowledge distillation(KD)object detectiontensor decomposition(TD)unmanned aerial vehi-cles(UAVs)

Nianyin Zeng、Xinyu Li、Peishu Wu、Han Li、Xin Luo

展开 >

Department of Instrumental and Electrical Engineering,Xiamen University,Xiamen 361005,China

College of Computer and Information Science,South-west University,Chongqing 400715,China

National Natural Science Foundation of ChinaNatural Science Foundation for Distinguished Young Scholars of the Fujian Province of ChinaFundamental Research Funds for the Central Universities of China

620732712023J0601020720220076

2024

10.1109/JAS.2023.124029

自动化学报(英文版)
中国自动化学会,中国科学院自动化研究所,中国科技出版传媒股份有限公司

自动化学报(英文版)

CSTPCDEI
ISSN：2329-9266
年,卷(期)：2024.11(2)
  • 64