融合注意力机制的弱监督语义分割自激活方法  

Self-Activated Learning Method for Weakly Supervised Semantic Segmentation Integrating Attention Mechanism

作　　者：周凯 于莲芝[1] ZHOU Kai;YU Lianzhi(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《电子科技》2025年第4期80-86,共7页Electronic Science and Technology

基　　金：国家自然科学基金(61603257)。

摘　　要：弱监督语义分割以类激活图进行训练,但类激活图与真实像素级标签存在较大差距。针对弱监督语义分割类激活图定位信息少、分割结果的轮廓粗糙问题,文中提出基于注意力机制的弱监督语义分割自激活模型。利用仿射变化引入全监督方法中的隐性约束,提取分类网络浅层信息并融合注意力机制。利用增强后的浅层信息细化类激活图的轮廓,根据生成的类激活图对特征图进行自激活,从而生成最终的类激活图。在PASCAL VOC 2012数据集上进行实验,相较于近期先进模型,类激活图的平均交并比提升了1.7%,最终分割结果的平均交并比提升了2.4%。通过对模型进行消融实验验证了各模块的有效性。Weakly supervised semantic segmentation is typically trained by class activation maps,but there is a significant gap between class activation maps and real pixel-level labels.A self-activation model of weakly supervised semantic segmentation based on attention mechanism is proposed to solve the problem that class activation maps of weakly supervised semantic segmentation have little positioning information and rough contour of segmentation results.The implicit constraints in the full supervision method are introduced by affine changes,the shallow information of the classification network is extracted and the attention mechanism is integrated.The enhanced shallow information is used to refine the outline of the class activation diagram,and the feature diagram is self-activated according to the generated class activation diagram,so as to generate the final class activation diagram.Experiments on the PASCAL VOC 2012 data set show a 1.7%improvement in the average crossover ratio of class activation graphs and a 2.4%improvement in the average crossover ratio of final segmentation results compared to recent advanced models.The effectiveness of each module is verified by the ablation experiments.

关 键 词：弱监督方法 语义分割 类激活图 注意力机制 卷积神经网络 自激活方法 仿射变换 浅层网络 隐性约束 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]