MDI-YOLO a lightweight transformer-CNN-based multidimensional feature fusion model for small object detection

Abstract To address the problem of insufficient detection accuracy in drone aerial and remote sensing images due to factors such as small target size, background interference, and occlusion, we propose a lightweight small object detection model, MDI-YOLO, based on multi-dimensional feature fusion of...

Descrición completa

Detalles Bibliográficos

Principais autores:	Hong Shi, Yiming Wu, Yong Xu, Xiaofang Mu, Mingxing Hou, Bowen Shi, Lingxiao Zhang
Formato:	Artigo
Idioma:	Inglês
Publicado:	Nature Portfolio 2026-02-01
Series:	Scientific Reports
Assuntos:	Small object detection Transformer YOLOv8 DFA Inner-Shape-IoU
Acceso en liña:	https://doi.org/10.1038/s41598-026-38378-x
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!