A Novel Data Augmentation Scheme for Pedestrian Detection with Attribute Preserving GAN
Liu, Songyan1,2; Guo, Haiyun1,2; Hu, Jian-Guo3; Zhao, Xu1,2; Zhao, Chaoyang1,2; Wang, Tong1,2; Zhu, Yousong1,2; Wang, Jinqiao1,2; Tang, Ming1,2
发表期刊Neurocomputing
ISSN0925-2312
2020-08-11
卷号401期号:11页码:123-132
摘要

Recently pedestrian detection has progressed significantly. However, detecting pedestrians of small scale or in heavy occlusions is still notoriously difficult. Besides, the generalization ability of pre-trained detectors across different datasets remains to be improved. Both of these issues can be attributed to insufficient training data coverage. To cope with this, we present an efficient data augmentation scheme by transferring pedestrians from other datasets into the target scene with a novel Attribute Preserving Generative Adversarial Networks (APGAN). The proposed methodology consists of two steps: pedestrian embedding and style transfer. The former step can simulate pedestrian images of various scale and occlusion, in any pose or background, thus greatly promoting the data variation. The latter step aims to make the generated samples more realistic while guarantee the data coverage. To achieve this goal, we propose APGAN, which pursues both good visual quality and attribute preserving after style transfer. With the proposed method, we can make effective sample augmentations to improve the generalization ability of the trained detectors and enhance its robustness to scale change and occlusions. Extensive experiment results validate the effectiveness and advantages of our method.

关键词Generative Adversarial Networks Pedestrian detection Data augmentation
DOI10.1016/j.neucom.2020.02.094
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[61806200] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61806200]
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000544725700012
出版者ELSEVIER
七大方向——子方向分类目标检测、跟踪与识别
引用统计
被引频次:24[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/39134
专题模式识别国家重点实验室_图像与视频分析
通讯作者Guo, Haiyun; Hu, Jian-Guo
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Sun Yat-Sen University, Guangzhou 510000, China
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Liu, Songyan,Guo, Haiyun,Hu, Jian-Guo,et al. A Novel Data Augmentation Scheme for Pedestrian Detection with Attribute Preserving GAN[J]. Neurocomputing,2020,401(11):123-132.
APA Liu, Songyan.,Guo, Haiyun.,Hu, Jian-Guo.,Zhao, Xu.,Zhao, Chaoyang.,...&Tang, Ming.(2020).A Novel Data Augmentation Scheme for Pedestrian Detection with Attribute Preserving GAN.Neurocomputing,401(11),123-132.
MLA Liu, Songyan,et al."A Novel Data Augmentation Scheme for Pedestrian Detection with Attribute Preserving GAN".Neurocomputing 401.11(2020):123-132.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
1-s2.0-S092523122030(2691KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Liu, Songyan]的文章
[Guo, Haiyun]的文章
[Hu, Jian-Guo]的文章
百度学术
百度学术中相似的文章
[Liu, Songyan]的文章
[Guo, Haiyun]的文章
[Hu, Jian-Guo]的文章
必应学术
必应学术中相似的文章
[Liu, Songyan]的文章
[Guo, Haiyun]的文章
[Hu, Jian-Guo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 1-s2.0-S0925231220302903-main.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。