计算机应用 ›› 2021, Vol. 41 ›› Issue (1): 208-214.DOI: 10.11772/j.issn.1001-9081.2020060968

所属专题: 第八届中国数据挖掘会议(CCDM 2020)

• 第八届中国数据挖掘会议(CCDM 2020) • 上一篇    下一篇

基于多级全局信息传递模型的视觉显著性检测

温静, 宋建伟   

  1. 山西大学 计算机与信息技术学院, 太原 030006
  • 收稿日期:2020-05-31 修回日期:2020-07-15 出版日期:2021-01-10 发布日期:2020-11-12
  • 通讯作者: 温静
  • 作者简介:温静(1982-),女,山西晋中人,副教授,博士,CCF会员,主要研究方向:计算机视觉、图像处理、模式识别;宋建伟(1994-),男,山西太原人,硕士研究生,主要研究方向:计算机视觉、图像处理。
  • 基金资助:
    国家自然科学青年基金资助项目(61703252);山西省应用基础研究计划项目(201701D121053)。

Visual saliency detection based on multi-level global information propagation model

WEN Jing, SONG Jianwei   

  1. School of Computer and Information Technology, Shanxi University, Taiyuan Shanxi 030600, China
  • Received:2020-05-31 Revised:2020-07-15 Online:2021-01-10 Published:2020-11-12
  • Supported by:
    This work is partially supported by the Youth Program of National Natural Science Foundation of China (61703252), the Shanxi Applied Basic Research Program (201701D121053).

摘要: 对神经网络中的卷积特征采用分层处理的思想能明显提升显著目标检测的性能。然而,在集成分层特征时,如何获得丰富的全局信息以及有效融合较高层特征空间的全局信息和底层细节信息仍是一个没有解决的问题。为此,提出了一种基于多级全局信息传递模型的显著性检测算法。为了提取丰富的多尺度全局信息,在较高层级引入了多尺度全局特征聚合模块(MGFAM),并且将多层级提取出的全局信息进行特征融合操作;此外,为了同时获得高层特征空间的全局信息和丰富的底层细节信息,将提取到的有判别力的高级全局语义信息以特征传递的方式和较低层次特征进行融合。这些操作可以最大限度提取到高级全局语义信息,同时避免了这些信息在逐步传递到较低层时产生的损失。在ECSSD、PASCAL-S、SOD、HKU-IS等4个数据集上进行实验,实验结果表明,所提算法相较于较先进的NLDF模型,其F-measure(F)值分别提高了0.028、0.05、0.035和0.013,平均绝对误差(MAE)分别降低了0.023、0.03、0.023和0.007。同时,所提算法在准确率、召回率、F-measure值及MAE等指标上也优于几种经典的图像显著性检测方法。

关键词: 显著性检测, 全局信息, 神经网络, 信息传递, 多尺度池化

Abstract: The idea of hierarchical processing of convolution features in neural networks has a significant effect on saliency object detection. However, when integrating hierarchical features, it is still an open problem how to obtain rich global information, as well as effectively integrate the global information and of the higher-level feature space and low-level detail information. Therefore, a saliency detection algorithm based on a multi-level global information propagation model was proposed. In order to extract rich multi-scale global information, a Multi-scale Global Feature Aggregation Module (MGFAM) was introduced to the higher-level, and feature fusion operation was performed to the global information extracted from multiple levels. In addition, in order to obtain the global information of the high-level feature space and the rich low-level detail information at the same time, the extracted discriminative high-level global semantic information was fused with the lower-level features by means of feature propagation. These operations were able to extract the high-level global semantic information to the greatest extent, and avoid the loss of this information when it was gradually propagated to the lower-level. Experimental results on four datasets including ECSSD,PASCAL-S,SOD,HKU-IS show that compared with the advanced NLDF (Non-Local Deep Features for salient object detection) model, the proposed algorithm has the F-measure (F) value increased by 0.028、0.05、0.035 and 0.013 respectively, the Mean Absolute Error (MAE) decreased by 0.023、0.03、0.023 and 0.007 respectively, and the proposed algorithm was superior to several classical image saliency detection methods in terms of precision, recall, F-measure and MAE.

Key words: saliency detection, global information, neural network, information propagation, multi-scale pooling

中图分类号: