KANs-DETR: Enhancing Detection Transformer with Kolmogorov–Arnold Networks for small object

This research proposed an end-to-end object detection network based on Kolmogorov–Arnold Networks (KANs)-Detection Transformer (DETR). KANs block was introduced into encoder–decoder structure instead of the full connection layer to dynamically learn the activation function and improve the robustness...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	High-Confidence Computing Ročník 6; číslo 1; s. 100336
Hlavní autori:	Zhang, Jingyu, Peng, Wentao, Xiao, Anyan, Liu, Tao, Fu, Junchao, Chen, Jian, Yan, Zhuo
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 01.03.2026 Elsevier
Predmet:	DETR Kolmogorov–Arnold networks Object detection SE networks Swin transformer DETR Swin transformer SE networks Kolmogorov–Arnold networks Object detection
ISSN:	2667-2952, 2667-2952
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	This research proposed an end-to-end object detection network based on Kolmogorov–Arnold Networks (KANs)-Detection Transformer (DETR). KANs block was introduced into encoder–decoder structure instead of the full connection layer to dynamically learn the activation function and improve the robustness and accuracy of the model. Experiments showed that the detection capability of KANs-DETR on multicategory object detection was better than that of HGNetv2 and Swin Transformer as backbone. Furthermore, in order to solve the problem of insensitivity to small objects, the Squeeze-and-Excitation module was applied for feature fusion and presented better performance. The KANs-DETR achieved high detection accuracy and efficiency in handling small objects in complex scenes, providing a new perspective for network optimization.
ISSN:	2667-2952 2667-2952
DOI:	10.1016/j.hcc.2025.100336