[1]许 畅,王朝辉.基于空间注意力的 CNN 特征增强方法[J].计算机技术与发展,2022,32(06):74-78.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 013]
　XU Chang,WANG Zhao-hui.Feature Augment of Convolutional Neural Network Based on Spatial Attention[J].,2022,32(06):74-78.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 013]
点击复制

基于空间注意力的 CNN 特征增强方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年06期
页码:
74-78
栏目:
图形与图像
出版日期:
2022-06-10

文章信息/Info

Title:
Feature Augment of Convolutional Neural Network Based on Spatial Attention
文章编号:
1673-629X(2022)06-0074-05
作者:
许 畅; 王朝辉
武汉科技大学 计算机科学与技术学院,湖北 武汉 430065
Author(s):
XU Chang; WANG Zhao-hui
School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China
关键词:
计算机视觉; 卷积神经网络; 空间注意力; 特征增强; 高频噪声抑制
Keywords:
computer vision; convolution neural network; spatial attention; feature augment; high frequency noise suppression
分类号:
TP391. 41
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 013
摘要:
卷积神经网络一般被用于特征提取,它通过提取图像底层的点、线、面的几何特征,进而映射到高层的语义特征,然而传统的卷积网络只对输入的样本进行宽泛的特征提取,而不会刻意去区分图像的前景和后景,这使得模型提取到的特征包含大量的背景噪声,降低了模型的表征能力。 在空间注意力的基础上,提出了一种名为特征增强网络( FA-block)的卷积网络分支,这种网络结构从样本的掩膜中学习目标的空间分布,为原始特征图上的每一个像素点训练得到代表重要程度的权重,然后通过加权的方式突出特征图中的目标部位。 此方法旨在抑制背景噪声,增强待学习的目标特征,让主干网络提取到的特征更加纯净。 在 PASCAL VOC 数据集上的实验证明了 FA-block 的有效性,最后经过 MS COCO 数据集的验证,FA-block 使得 Faster Rcnn 基线的性能提高了 5. 5% 。
Abstract:
Convolutional neural network is generally used for feature extraction. It extracts the geometric features of points, lines andsurfaces at the bottom of the image,and then maps them to high-level semantic features. However,the traditional convolution networkonly extracts general features from the input samples,instead of deliberately distinguishing the foreground and background,which makesthe features extracted by the model contain a lot of background noise and weakens its representation ability. On the basis of spatialattention,a convolution branch called feature augment block(FA-block) is proposed. This network structure learns the spatial distributionof the target from the mask of the sample and acquires a weight representing the importance degree for each pixel,then highlights thetarget part by weighting. This method aims to suppress background noise and augment the target features to be learned,make the featuresextracted from the backbone network more pure. The experiment on Pascal VOC dataset proves the effectiveness of FA-block. Throughthe validation of MS COCO dataset,FA-block improves the performance of a group of baselines of Faster Rcnn by 5. 5% .

相似文献/References:

[1]黄艳 赵越.3D靶标的摄像机三步标定算法与实现[J].计算机技术与发展,2010,(01):135.
　HUANG Yan,ZHAO Yue.Algorithm and Realization of Three-step Camera Calibration Based on 3D-Target[J].,2010,(06):135.
[2]付海洋 牛连强 刘守琳.一种基于平面模板的单应矩阵求解方法[J].计算机技术与发展,2010,(04):69.
　FU Hai-yang,NIU Lian-qiang,LIU Shou-lin.A Solving Homography Matrix Method Based on Planar Pattern[J].,2010,(06):69.
[3]张铖伟 王彪 徐贵力.摄像机标定方法研究[J].计算机技术与发展,2010,(11):174.
　ZHANG Cheng-wei,WANG Biao,XU Gui-li.A Study on Classification of Camera Calibration Methods[J].,2010,(06):174.
[4]毛雁明 杨慧玲.一种新的立体匹配算法[J].计算机技术与发展,2011,(03):105.
　MAO Yan-ming,YANG Hui-ling.A New Stereo Matching Algorithm[J].,2011,(06):105.
[5]杨晟,李学军,王珏,等.连续尺度复合分析核线重排列影像准稠密匹配[J].计算机技术与发展,2013,(04):111.
　YANG Sheng,LI Xue-jun,WANG Jue,et al.Continuous Scale Multi-change Detecting Quasi-dense Matching for Epipolar Resample Images[J].,2013,(06):111.
[6]卢振宇,郭星,魏赛,等.基于计算机视觉的虚拟安全空间预警技术[J].计算机技术与发展,2014,24(02):237.
　LU Zhen-yu,GUO Xing,WEI Sai,et al.A Surveillance Technology for Virtual Security Space Based on Computer Vision[J].,2014,24(06):237.
[7]李孟,周波,孟正大,等. 三目立体相机的标定研究[J].计算机技术与发展,2015,25(02):69.
　LI Meng,ZHOU Bo,MENG Zheng-da,et al. Study on Trinocular Stereo Camera Calibration[J].,2015,25(06):69.
[8]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].,2018,28(06):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[9]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(06):31.
[10]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(06):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[11]许必宵,宫 婧,孙知信.基于卷积神经网络的目标检测模型综述[J].计算机技术与发展,2019,29(12):87.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 016]
　XU Bi-xiao,GONG Jing,SUN Zhi-xin.A Survey of Object Detection Models Based on Convolutional Neural Networks[J].,2019,29(06):87.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 016]

更新日期/Last Update: 2022-06-10