帮助 关于我们

返回检索结果

基于多粒度特征融合网络的行人重识别
Multi-granularity Feature Fusion Network for Person Re-Identification

查看参考文献33篇

匡澄   陈莹 *  
文摘 行人重识别旨在跨监控设备下检索出特定的行人目标.为捕捉行人图像的多粒度特征进而提高识别精度,基于OSNet基准网络提出一种多粒度特征融合网络(Multi-granularity Feature Fusion Network for Person Re-Identification, MFN)进行端对端的学习. MFN由全局分支、特征擦除分支和局部分支组成,其中特征擦除分支由双通道注意力擦除模型构成,此模型包含通道注意力擦除模块(Channel Attention-based Dropout Moudle, CDM)和空间注意力擦除模块(Spatial Attention-based Dropout Moudle, SDM). CDM对通道的注意力强度排序并擦除低注意力通道,SDM在空间维度上以一定概率擦除最具有判别力的特征,两者通过并联方式相互作用,提高模型的识别能力.全局分支采用特征金字塔结构提取多尺度特征,局部分支将特征均匀切块后级联成一个单一特征,提取关键局部信息.大量实验结果表明了本文方法的有效性,在Market1501、DukeMTMC-reID和CUHK03-Labeled(Detected)数据集上,mAP/Rank-1分别达到了90.1%/95.8%、81.8%/91.4%和80.7%/82.3%(78.7%/81.6%),大幅优于其他现有方法.
其他语种文摘 For the purpose of capturing the multi-granularity features and improving the recognition accuracy, a multi-granularity feature fusion network for person re-identification (MFN) is proposed based on the omist-scale network (OSNet). The MFN network is composed of a global branch, a feature dropout branch and a local branch. The feature dropout branch consists of a dual-channel attention dropout model, which includes a channel attention-based dropout moudle (CDM) and a Spatial attention-based dropout moudle (SDM). CDM sorts the attention intensity and dropouts low attention channels, and SDM dropouts the most discriminative features with a certain probability in the spatial dimension. The global branch uses the feature pyramid structure to extract multi-scale features, and the local branch employs a uniform partition strategy to produce local features which are cascaded into a single one for key local information extraction. Experiments on the large scale datasets show the effectiveness of MFN. On the Market1501, DukeMTMC-reID and CUHK03 -Labeled (Detected) datasets, mAP/Rank-1 of MFN reaches 90.1%/95.8%, 81.8%/91.4% and 80.7%/82.3% (78.7%/81.6%), which is superior to other existing methods.
来源 电子学报 ,2021,49(8):1541-1550 【核心库】
DOI 10.12263/DZXB.20200974
关键词 行人重识别 ; 多分支CNN网络 ; 金字塔结构 ; 特征擦除
地址

江南大学, 轻工过程先进控制教育部重点实验室, 江苏, 无锡, 214122

语种 中文
文献类型 研究性论文
ISSN 0372-2112
学科 自动化技术、计算机技术
基金 国家自然科学基金
文献收藏号 CSCD:7055897

参考文献 共 33 共2页

1.  罗浩. 基于深度学习的行人重识别研究进展. 自动化学报,2019,45(11):2032-2049 CSCD被引 67 次    
2.  Weinberger K Q. Fast solvers and efficient implementations for distance metric learning. Proceedings of the 25th International Conference on Machine Learning,2008:1160-1167 CSCD被引 6 次    
3.  Liao S. Person re-identification by local maximal occurrence representation and metric learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:2197-2206 CSCD被引 15 次    
4.  Sun Y. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). Proceedings of the European Conference on Computer Vision,2018:480-496 CSCD被引 13 次    
5.  Wang G. Learning discriminative features with multiple granularities for person re-identification. Proceedings of the 26th ACM International Conference on Multimedia,2018:274-282 CSCD被引 28 次    
6.  陈巧媛. 通道互注意机制下的部位对齐行人再识别. 计算机辅助设计与图形学学报,2020,32(8):1258-1266 CSCD被引 2 次    
7.  Zheng F. Pyramidal person re-identification via multi-loss dynamic training. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2019:8514-8522 CSCD被引 5 次    
8.  DeVries T. Improved regularization of convolutional neural networks with cutout,2017 CSCD被引 31 次    
9.  Zhong Z. Random erasing data augmentation. Association for the Advance of Artificial Intelligence,2020:13001-13008 CSCD被引 2 次    
10.  Ghiasi G. Dropblock:A regularization method for convolutional networks. Neural Information Processing Systems,2018:10727-10737 CSCD被引 1 次    
11.  Tompson J. Efficient object localization using convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:648-656 CSCD被引 15 次    
12.  Dai Z. Batch DropBlock network for person re-identification and beyond. Proceedings of the IEEE International Conference on Computer Vision,2019:3691-3701 CSCD被引 4 次    
13.  Zhou K. Omni-scale feature learning for person re-identification. Proceedings of the IEEE International Conference on Computer Vision,2019:3702-3712 CSCD被引 4 次    
14.  Zheng L. Scalable person re-identification:A benchmark. Proceedings of The IEEE International Conference on Computer Vision,2015:1116-1124 CSCD被引 75 次    
15.  Ristani E. Performance measures and a data set for multi-target,multi-camera tracking. European Conference on Computer Vision,2016:17-35 CSCD被引 36 次    
16.  Li W. Deepreid:Deep filter pairing neural network for person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:152-159 CSCD被引 34 次    
17.  Chen T. Abd-net:Attentive but diverse person re-identification. Proceedings of the IEEE International Conference on Computer Vision,2019:8351-8361 CSCD被引 4 次    
18.  Lin T Y. Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017:2117-2125 CSCD被引 505 次    
19.  Lin T Y. Microsoft coco: Common objects in context. European Conference on Computer Vision,2014:740-755 CSCD被引 268 次    
20.  Choe J. Attention-based dropout layer for weakly supervised object localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2019:2219-2228 CSCD被引 2 次    
引证文献 6 篇

1 孙劲光 基于多尺度加权特征融合的行人重识别方法研究 信号处理,2022,38(10):2201-2210
CSCD被引 1 次

2 陈莹 基于CNN和TransFormer多尺度学习行人重识别方法 电子与信息学报,2023,45(6):2256-2263
CSCD被引 1 次

显示所有6篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号