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

Unmanned aerial vehicles(UAVs) have gained significant attention in practical applications, especially the low-altitude aerial(LAA) object detection imposes stringent requirements 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 equalweighted response-based KD(knowledge distillation) methods are designed to minimize redundant parameters while ensuring comparable 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 regression 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 comparison 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 realizing domain adaptation.

A Local-Global Attention Fusion Framework With Tensor Decomposition for Medical Diagnosis

Dear Editor,In this letter,a novel hierarchical fusion framework is proposed to address the imperfect data property in complex medical image analysis(MIA)scenes.In particular,by combining the strengths of convolutional neural networks(CNNs)and transformers,the enhanced feature extraction,spatial modeling,and sequential context learning are realized to provide comprehensive insights on the complex data patterns.Integration of information in different level is enabled via a multi-attention fusion mechanism,and the tensor decomposition methods are adopted so that compact and distinctive representation of the underlying and high-dimensional medical image features can be accomplished[1].It is shown from the evaluation results that the proposed framework is competitive and superior as compared with some other advanced algorithms,which effectively handles the imperfect property of inter-class similarity and intra-class differences in diseases,and meanwhile,the model complexity is reduced within an acceptable level,which benefits the deployment in clinic practice.MIA has assumed a pivotal role in numerous critical clinical scenarios,where sophisticated image analysis techniques have proven instrumental in augmenting medical decision-making,facilitating individualized therapeutic interventions,and enhancing patient prognostication[2]−[4].