摘要
为解决行人重识别研究领域中行人标注图像获取困难的问题,提出一种多因素引导的行人数据增广方法。首先,在生成器网络中设计了一种局部多尺度引导机制,通过特征融合抑制生成图像的局部伪影;其次,提出了长距离相关性引导机制,通过外注意力引导生成图像的长距离依赖,提高生成行人图像的整体视感质量;最后,提出一种抗博弈判别网络,通过嵌入到生成对抗网络,从而构建一种三网络稳定博弈架构模型,增加生成对抗网络训练的稳定性。通过VIPeR、Market-1501、DukeMTMC-reID这3种不同规模数据集的仿真实验,结果表明该方法与目前主流方法相比,mAP与Rank-1精度上均有不同程度的提升,在小规模数据集上的提升较为显著。
To solve the difficulty in obtaining annotated pedestrian images in the field of pedestrian re-identification research,a novel data augmentation method guided by multi-factor is proposed in this paper.Firstly,a local multi-scale guidance mechanism is designed in the generator network.It can suppress the local artifacts in generated images through feature fusion.Secondly,a long-distance correlation guidance mechanism is proposed to improve the overall visual quality of the generated pedestrian image by guiding the long-distance dependence of the generated image with external attention.Lastly,an adversarial discrimination network is designed and embed into original generative adversarial networks.The three network stability architecture model increases the stability of generative adversarial network training.The experiment are validated on the VIPeR,Market-1501 and DukeMTMC-reID benchmark datasets.The results demonstrate our method outperforms the state-of-the-art with the mAP and rank-1 scores,especially in small-scale datasets.
作者
刘志刚
张国辉
高月
刘苗苗
LIU Zhigang;ZHANG Guohui;GAO Yue;LIU Miaomiao(School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China;Heilongjiang Petroleum Big Data and Intelligent Analysis Key Laboratory,Daqing 163318,China)
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
2024年第2期235-242,共8页
Journal of University of Electronic Science and Technology of China
基金
国家自然科学基金(51774090,42002138)
黑龙江省自然科学基金(LH2020F003)
河北省自然科学基金(D2023107002)
黑龙江省属本科高校团队创新基金(2022TSTD-03)
黑龙江省高等教育教学改革项目(SJGY20210109)。
关键词
行人重识别
生成对抗网络
数据增广
局部多尺度
注意力机制
person re-identification
generative adversial network
data augmentation
local multi-scale
attention mechanism