提出HRDecoder，高效分割眼底图像病灶，兼顾精度与速度。
HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation
- 通过高分辨率特征学习与多尺度融合，保留细节并捕捉上下文。
- 在IDRiD和DDR数据集上提升分割精度，内存与计算开销可控。
- 适合需要高精度眼底病灶分割的临床辅助诊断场景。
高分辨率对眼底图像精确分割至关重要，但处理高分辨率输入会带来巨大显存开销，且性能增益随开销增加而减弱。为解决此问题并应对微小病灶分割挑战，现有研究采用局部-全局融合方法，利用局部区域保留细粒度特征，从下采样全局图像中获取长程上下文信息。然而，多次前向传播不可避免地引入显著计算开销，影响推理速度。本文提出HRDecoder，一种用于眼底病变分割的高分辨率解码器网络。其集成高分辨率表征学习模块以捕获精细局部特征，并设计高分辨率融合模块实现多尺度预测融合。该方法在保持合理内存与计算开销的同时，显著提升眼底病灶整体分割精度，并维持良好推理速度。在IDRiD和DDR数据集上的实验结果验证了方法的有效性。代码已开源：https://github.com/CVIU-CSU/HRDecoder。
原文摘要 · Abstract (English)
High resolution is crucial for precise segmentation in fundus images, yet handling high-resolution inputs incurs considerable GPU memory costs, with diminishing performance gains as overhead increases. To address this issue while tackling the challenge of segmenting tiny objects, recent studies have explored local-global fusion methods. These methods preserve fine details using local regions and capture long-range context information from downscaled global images. However, the necessity of multiple forward passes inevitably incurs significant computational overhead, adversely affecting inference speed. In this paper, we propose HRDecoder, a simple High-Resolution Decoder network for fundus lesion segmentation. It integrates a high-resolution representation learning module to capture fine-grained local features and a high-resolution fusion module to fuse multi-scale predictions. Our method effectively improves the overall segmentation accuracy of fundus lesions while consuming reasonable memory and computational overhead, and maintaining satisfying inference speed. Experimental results on the IDRiD and DDR datasets demonstrate the effectiveness of our method. Code is available at https://github.com/CVIU-CSU/HRDecoder.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。