arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05310cs.CV
收藏

基于生物启发的表示学习的视觉注意预测

Bio-Inspired Representation Learning for Visual Attention Prediction

Northwestern Polytechnical University(西北工业大学);Chinese Academy of Sciences(中国科学院);University of Chinese Academy of Sciences(中国科学院大学)

Yuan Yuan, Hailong Ning, Xiaoqiang Lu

摘要:

视觉注意力预测(VAP)是计算机视觉领域中一个重要而迫切的研究课题。现有的VAP方法大多基于深度学习。然而,他们没有充分利用低层次的对比度功能,同时产生的视觉注意力地图。提出了一种基于生物启发表示学习的视觉注意图生成方法。仿生表示学习同时结合了图像的低对比度和高语义特征,这是由于人眼对高对比度的图像块和高语义的图像对象非常敏感。该方法由三个主要步骤组成:1)特征提取,2)生物启发的表示学习和3)视觉注意图生成。首先,从改进的VGG 16中提取高级语义特征,而通过深度网络中的所提出的对比度特征提取块来提取低级对比度特征。其次,在生物启发的表示学习,无论是提取的低层次的对比度和高层次的语义特征相结合的设计密集连接的块,这是建议连接的各种功能规模的规模。最后,加权融合层被用来生成最终的视觉注意力地图的基础上获得的表示后,生物启发表示学习。大量的实验证明了该方法的有效性。

英文摘要:

Visual Attention Prediction (VAP) is a significant and imperative issue in the field of computer vision. Most of existing VAP methods are based on deep learning. However, they do not fully take advantage of the low-level contrast features while generating the visual attention map. In this paper, a novel VAP method is proposed to generate visual attention map via bio-inspired representation learning. The bio-inspired representation learning combines both low-level contrast and high-level semantic features simultaneously, which are developed by the fact that human eye is sensitive to the patches with high contrast and objects with high semantics. The proposed method is composed of three main steps: 1) feature extraction, 2) bio-inspired representation learning and 3) visual attention map generation. Firstly, the high-level semantic feature is extracted from the refined VGG16, while the low-level contrast feature is extracted by the proposed contrast feature extraction block in a deep network. Secondly, during bio-inspired representation learning, both the extracted low-level contrast and high-level semantic features are combined by the designed densely connected block, which is proposed to concatenate various features scale by scale. Finally, the weighted-fusion layer is exploited to generate the ultimate visual attention map based on the obtained representations after bio-inspired representation learning. Extensive experiments are performed to demonstrate the effectiveness of the proposed method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑