Research on Improving the High Precision and Lightweight Diabetic Retinopathy Detection of YOLOv8n
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908429443923968 |
|---|---|
| author | Yuhuan, Fei Xufei, Sun Ran, Zang Gengchen, Wang Meng, Su Fenghao, Liu |
| author_facet | Yuhuan, Fei Xufei, Sun Ran, Zang Gengchen, Wang Meng, Su Fenghao, Liu |
| contents | Early detection and diagnosis of diabetic retinopathy is one of the current research focuses in ophthalmology. However, due to the subtle features of micro-lesions and their susceptibility to background interference, ex-isting detection methods still face many challenges in terms of accuracy and robustness. To address these issues, a lightweight and high-precision detection model based on the improved YOLOv8n, named YOLO-KFG, is proposed. Firstly, a new dynamic convolution KWConv and C2f-KW module are designed to improve the backbone network, enhancing the model's ability to perceive micro-lesions. Secondly, a fea-ture-focused diffusion pyramid network FDPN is designed to fully integrate multi-scale context information, further improving the model's ability to perceive micro-lesions. Finally, a lightweight shared detection head GSDHead is designed to reduce the model's parameter count, making it more deployable on re-source-constrained devices. Experimental results show that compared with the base model YOLOv8n, the improved model reduces the parameter count by 20.7%, increases mAP@0.5 by 4.1%, and improves the recall rate by 7.9%. Compared with single-stage mainstream algorithms such as YOLOv5n and YOLOv10n, YOLO-KFG demonstrates significant advantages in both detection accuracy and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00780 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Research on Improving the High Precision and Lightweight Diabetic Retinopathy Detection of YOLOv8n Yuhuan, Fei Xufei, Sun Ran, Zang Gengchen, Wang Meng, Su Fenghao, Liu Image and Video Processing Computer Vision and Pattern Recognition Early detection and diagnosis of diabetic retinopathy is one of the current research focuses in ophthalmology. However, due to the subtle features of micro-lesions and their susceptibility to background interference, ex-isting detection methods still face many challenges in terms of accuracy and robustness. To address these issues, a lightweight and high-precision detection model based on the improved YOLOv8n, named YOLO-KFG, is proposed. Firstly, a new dynamic convolution KWConv and C2f-KW module are designed to improve the backbone network, enhancing the model's ability to perceive micro-lesions. Secondly, a fea-ture-focused diffusion pyramid network FDPN is designed to fully integrate multi-scale context information, further improving the model's ability to perceive micro-lesions. Finally, a lightweight shared detection head GSDHead is designed to reduce the model's parameter count, making it more deployable on re-source-constrained devices. Experimental results show that compared with the base model YOLOv8n, the improved model reduces the parameter count by 20.7%, increases mAP@0.5 by 4.1%, and improves the recall rate by 7.9%. Compared with single-stage mainstream algorithms such as YOLOv5n and YOLOv10n, YOLO-KFG demonstrates significant advantages in both detection accuracy and efficiency. |
| title | Research on Improving the High Precision and Lightweight Diabetic Retinopathy Detection of YOLOv8n |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.00780 |