同济大学学报（自然科学版）2024，Vol.52Issue(2)：293-302,10.DOI:10.11908/j.issn.0253-374x.22220
边缘信息增强的显著性目标检测网络
Edge Enhancing Network for Salient Object Detection
摘要
Abstract
Aiming at the problem of blurred edges in salient object detection,this paper proposes a new method that can fully utilize edge information to enhance the confidence of edge pixels.First,the triple attention module is introduced,which uses the characteristics of the predicted saliency map to directly generate foreground,background and edge attention,and the process of generating attention weights does not add any parameters.Next,the edge prediction module is introduced,which performs supervised edge prediction in the shallowest layer of the network with the biggest feature map,and fuses the predicted edge with the saliency map to refine the edges.Finally,the model is qualitatively and is quantitatively evaluated on six commonly used public datasets,and fully compared with other models,which proves that the proposed model can achieve the best results.The method proposed in this paper has 30.28 M parameters,and can predict saliency maps at 31 frames per second on GTX 1080 Ti graphics card.关键词
显著性目标检测/注意力机制/边缘检测/深度卷积神经网络Key words
salient object detection/attention mechanism/boundary detection/deep convolutional neural network分类
信息技术与安全科学引用本文复制引用
赵卫东,王辉,柳先辉..边缘信息增强的显著性目标检测网络[J].同济大学学报（自然科学版）,2024,52(2):293-302,10.基金项目
上海市科技计划项目(20DZ2281000) （20DZ2281000）
