Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2507.00780

Research on Improving the High Precision and Lightweight Diabetic Retinopathy Detection of YOLOv8n

Fei Yuhuan·Sun Xufei·Zang Ran·Wang Gengchen·Su Meng·Liu Fenghao
View original source ↗Read source document ↗Export metadata ↓

Abstract

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.

Explore related subjects

eess.IVcs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Fei Yuhuan, Sun Xufei, Zang Ran, Wang Gengchen, Su Meng, Liu Fenghao. 2025-07-01. Research on Improving the High Precision and Lightweight Diabetic Retinopathy Detection of YOLOv8n. https://arxiv.org/abs/2507.00780

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Bridging the Inter-Domain Gap through Low-Level Features for Cross-Modal Medical Image Segmentation

This paper addresses cross-modal medical image segmentation, focusing on MRI-CT transfer in a source-only domain generalization setting. During training, only source-modality samples are available, while unlabeled target-modality images are used for testing. We propose LowBridge, which builds on the observation that cross-modal images share similar low-level features (e.g. edges) as they depict the same types of anatomical structures. Specifically, we first train a generative model to recover the source images from their edge features, followed by training a segmentation model on the generated source images, separately. At test time, edge features from the target images are input to the pretrained generative model to generate source-style target domain images, which are then segmented using the pretrained segmentation network. Experiments on various public datasets demonstrate that LowBridge achieves state-of-the-art performance, outperforming ten existing approaches. Ablation studies further show that LowBridge is compatible with different types of generative and segmentation models, suggesting its generalizability and potential to benefit from future advances in these models. The code will be available at https://github.com/JoshuaLPF/LowBridge.

eess.IV↗
arXiv2026

Revolutionizing Diffusion MRI Microstructure Mapping via Global Inversion

Diffusion MRI microstructure mapping (MM) is conventionally solved voxel by voxel, ignoring the fact that tissue microstructure forms a spatially organized field. This isolation leaves each estimation problem ill-posed and nonconvex. We instead cast MM as a single global inverse problem, reconstructing the entire parameter field jointly from all measurements of a subject. An untrained neural representation supplies implicit spatial priors and eases the nonconvex optimization, requiring no training data, while coregistered T1-weighted anatomy contributes structural guidance that is freely available in standard protocols. On both synthetic and in-vivo data, our method compares favorably with established voxel-wise and learning-based baselines, suggesting global inversion is a promising alternative.

eess.IV↗
arXiv2026

LC3EM: Long-Range Context Extrapolation Enhanced Entropy Model for Coordinate-based Overfitting Image Codecs

Coordinate-based overfitting image codecs have attracted increasing attention for their low decoding complexity and independence from cross-image generalization. However, representative approaches such as COOL-CHIC face an inherent entropy-modeling trade-off: lightweight models have limited capacity, while more expressive ones incur additional bitrate overhead from transmitting image-specific parameters. Inspired by the prediction mechanism in traditional codecs, we propose a new entropy-modeling strategy that introduces complementary prediction modes with region-adaptive soft mode selection, rather than relying on a single learned predictor to model diverse types of redundancy. Based on this concept, we develop a Long-Range Context Extrapolation Enhanced Entropy Model (LC3EM), which can be integrated into coordinate-based overfitting codecs. Specifically, a parameter-free Neighborhood-based Linear Extrapolation Mode (NLEM) complements the tiny MLP-based local predictor to exploit long-range contextual redundancy and strongly directional structures. A Minimum-Entropy-Inspired Continuous Mode Selection strategy is designed to adaptively fuse these two complementary modes, while requiring the transmission of only the parameters of a single additional linear layer. Moreover, to alleviate the mismatch between training-time relaxed and actual discrete quantization, we introduce a lightweight iterative latent rounding refinement stage to improve compression performance. Experiments demonstrate consistent improvements across diverse benchmarks, particularly on highly regular computer-generated images. When integrated with COOL-CHIC 4.0, the proposed method achieves BD-rate gains of -3.43\% and -7.69\% on the SIQAD and API datasets, respectively. With COOL-CHIC 5.0 as the backbone, the corresponding gains are -2.88\% and -3.15\%, respectively. The code will be made publicly available soon.

eess.IV↗