CASIA OpenIR  > 模式识别国家重点实验室  > 先进时空数据分析与学习
Density-Aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
Zhang, Chi1; Lin, Zihang1; Xu, Liheng1; Li, Zongliang1; Tang, Wei2; Liu, Yuehu1; Meng, Gaofeng3,4,5; Wang, Le1; Li, Li6
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN1051-8215
2022-07-01
Volume32Issue:7Pages:4552-4572
Corresponding AuthorLiu, Yuehu(liuyh@xjtu.edu.cn)
AbstractThe 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.
KeywordFeature extraction Image synthesis Scattering Generative adversarial networks Atmospheric modeling Training Testing Haze synthesis unsupervised image-to-image translation self-supervised disentanglement
DOI10.1109/TCSVT.2021.3130158
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Development Project of New Generation Artificial Intelligence of China[2018AAA0102504] ; National Natural Science Foundation of China[61973245]
Funding OrganizationNational Key Research and Development Project of New Generation Artificial Intelligence of China ; National Natural Science Foundation of China
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000819817700037
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/49195
Collection模式识别国家重点实验室_先进时空数据分析与学习
Corresponding AuthorLiu, Yuehu
Affiliation1.Xi An Jiao Tong Univ, Inst Artificial Intelligence & Robot, Xian 710049, Shaanxi, Peoples R China
2.Univ Illinois, Dept Comp Sci, Chicago, IL 60607 USA
3.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, HK Inst Sci & Innovat, Beijing 100190, Peoples R China
5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
6.Tsinghua Univ, Dept Automat, BNRist, Beijing 100084, Peoples R China
Recommended Citation
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.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Chi]'s Articles
[Lin, Zihang]'s Articles
[Xu, Liheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Chi]'s Articles
[Lin, Zihang]'s Articles
[Xu, Liheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Chi]'s Articles
[Lin, Zihang]'s Articles
[Xu, Liheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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