SIA OpenIR  > 光电信息技术研究室
融合注意力机制的多尺度目标检测算法
Alternative TitleMulti-Scale Target Detection Algorithm Based on Attention Mechanism
鞠默然1,2,3,4,5; 罗江宁6; 王仲博1,2,3,4,5; 罗海波1,2,4,5
Department光电信息技术研究室
Source Publication光学学报
ISSN0253-2239
2020
Volume40Issue:13Pages:1-9
Indexed ByEI
EI Accession number20203709153040
Contribution Rank1
Keyword卷积神经网络 特征融合 注意力机制 YOLO V3
Abstract

基于串联(concat)操作的特征融合方法仅仅融合了相邻尺度的特征,并没有充分利用来自其他尺度的输出特征。并且,串联操作只是在通道维度上将不同尺度的特征连接,不能反映不同通道间特征的相关性和重要性。针对这些问题,提出了一种基于注意力机制的特征融合算法。该算法利用注意力机制来融合不同尺度的特征,通过对每个通道的特征进行权重分配来学习不同通道间特征的相关性。将基于注意力机制的特征融合算法与YOLO V3相结合,构建多尺度目标检测器,并利用Focal loss和GIOU loss来设计检测器的损失函数。在PASCAL VOC和KITTI数据集上对不同算法进行对比实验,实验结果表明,多尺度目标检测器具有更高的检测精度和较快的检测速度。

Other Abstract

The feature fusion method based on concatenation (concat) operation only fuses features of adjacent scales without fully utilizing output features of other scales. Moreover,the concatenation operation only combines features of different scales in the channel dimension, which cannot reflect the correlation and importance of features between different channels. To address these challenges, a feature fusion algorithm based on attention mechanism is proposed. The proposed algorithm uses attention mechanism to fuse features of different scales and learns the correlation between features of different channels by considering the weight allocation of features of each channel. A multi-scale target detector is established by combining the feature fusion algorithm based on attention mechanism with YOLO V3;further, the loss function of detector is designed using Focal and GIOU losses. Comparative experimental results on PASCAL VOC and KITTI datasets show that the proposed multi-scale target detector can effectively improve the detection accuracy and speed.

Language中文
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/26918
Collection光电信息技术研究室
Corresponding Author罗海波
Affiliation1.中国科学院沈阳自动化研究所
2.中国科学院机器人与智能制造创新研究院
3.中国科学院大学
4.中国科学院光电信息处理重点实验室
5.辽宁省图像理解与视觉计算重点实验室
6.麦吉尔大学
Recommended Citation
GB/T 7714
鞠默然,罗江宁,王仲博,等. 融合注意力机制的多尺度目标检测算法[J]. 光学学报,2020,40(13):1-9.
APA 鞠默然,罗江宁,王仲博,&罗海波.(2020).融合注意力机制的多尺度目标检测算法.光学学报,40(13),1-9.
MLA 鞠默然,et al."融合注意力机制的多尺度目标检测算法".光学学报 40.13(2020):1-9.
Files in This Item:
File Name/Size DocType Version Access License
融合注意力机制的多尺度目标检测算法.pd(2695KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[鞠默然]'s Articles
[罗江宁]'s Articles
[王仲博]'s Articles
Baidu academic
Similar articles in Baidu academic
[鞠默然]'s Articles
[罗江宁]'s Articles
[王仲博]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[鞠默然]'s Articles
[罗江宁]'s Articles
[王仲博]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 融合注意力机制的多尺度目标检测算法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.