桂林电子科技大学学报2026，Vol.46Issue(4)：386-393,8.DOI:10.16725/j.1673-808X.2023205
基于标签交叉混合的多层多通道的涂鸦标注语义分割方法
Multi-layer and multi-channel semantic segmentation method for scribble annotation based on label cross-blending
摘要
Abstract
Weakly supervised semantic segmentation based on scribble annotations faces two major challenges:pseudo-labels used for model training are highly susceptible to noise,and existing methods exhibit limited capability in recognizing irregular targets.These challenges are particularly evident in cardiac image segmentation tasks.To address these issues,a multi-layered,multi-chan-nel semantic segmentation framework based on label cross-blending is proposed.A label cross-blending module is designed to ad-just the proportion of labeled pixels while suppressing noisy and incorrect annotations in the generated training samples.In addition,a novel network architecture is developed to exploit high-level feature representations extracted by convolutional neural networks(CNNs),enabling more effective characterization of irregular targets and improved boundary delineation to enhance model robust-ness and segmentation consistency.Experimental results on the public MSCMR and ACDC datasets demonstrate the effectiveness of the proposed method,achieving Dice similarity coefficients of 86.8%and 87.1%,respectively.关键词
语义分割/医学图像/涂鸦标注弱标签/注意力机制/先验知识Key words
semantic segmentation/medical images/scribble weak annotation/attention mechanism/prior knowledge分类
信息技术与安全科学引用本文复制引用
梅家铭,张艳菊..基于标签交叉混合的多层多通道的涂鸦标注语义分割方法[J].桂林电子科技大学学报,2026,46(4):386-393,8.基金项目
广西图像图形与智能处理重点实验室基金(GIIP2004) （GIIP2004）
