Density-Aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
文献类型:期刊论文
作者 | Zhang, Chi6; Lin, Zihang6; Xu, Liheng6; Li, Zongliang6; Tang, Wei5; Liu, Yuehu6; Meng, Gaofeng2,3,4; Wang, Le6; Li, Li1 |
刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY |
出版日期 | 2022-07-01 |
卷号 | 32期号:7页码:4552-4572 |
ISSN号 | 1051-8215 |
关键词 | Feature extraction Image synthesis Scattering Generative adversarial networks Atmospheric modeling Training Testing Haze synthesis unsupervised image-to-image translation self-supervised disentanglement |
DOI | 10.1109/TCSVT.2021.3130158 |
通讯作者 | Liu, Yuehu(liuyh@xjtu.edu.cn) |
英文摘要 | The key procedure of haze image synthesis with adversarial training lies in the disentanglement of the feature involved only in haze synthesis, i.e., the style feature, from the feature representing the invariant semantic content, i.e., the content feature. Previous methods introduced a binary classifier to constrain the domain membership from being distinguished through the learned content feature during the training stage, thereby the style information is separated from the content feature. However, we find that these methods cannot achieve complete content-style disentanglement. The entanglement of the flawed style feature with content information inevitably leads to the inferior rendering of haze images. To address this issue, we propose a self-supervised style regression model with stochastic linear interpolation that can suppress the content information in the style feature. Ablative experiments demonstrate the disentangling completeness and its superiority in density-aware haze image synthesis. Moreover, the synthesized haze data are applied to test the generalization ability of vehicle detectors. Further study on the relation between haze density and detection performance shows that haze has an obvious impact on the generalization ability of vehicle detectors and that the degree of performance degradation is linearly correlated to the haze density, which in turn validates the effectiveness of the proposed method. |
资助项目 | National Key Research and Development Project of New Generation Artificial Intelligence of China[2018AAA0102504] ; National Natural Science Foundation of China[61973245] |
WOS研究方向 | Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000819817700037 |
资助机构 | National Key Research and Development Project of New Generation Artificial Intelligence of China ; National Natural Science Foundation of China |
源URL | [http://ir.ia.ac.cn/handle/173211/49194] |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
通讯作者 | Liu, Yuehu |
作者单位 | 1.Tsinghua Univ, Dept Automat, BNRist, Beijing 100084, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, HK Inst Sci & Innovat, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 5.Univ Illinois, Dept Comp Sci, Chicago, IL 60607 USA 6.Xi An Jiao Tong Univ, Inst Artificial Intelligence & Robot, Xian 710049, Shaanxi, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Chi,Lin, Zihang,Xu, Liheng,et al. Density-Aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(7):4552-4572. |
APA | Zhang, Chi.,Lin, Zihang.,Xu, Liheng.,Li, Zongliang.,Tang, Wei.,...&Li, Li.(2022).Density-Aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(7),4552-4572. |
MLA | Zhang, Chi,et al."Density-Aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.7(2022):4552-4572. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。