文献类型：期刊文献

英文题名：Generative Adversarial and Self-Supervised Dehazing Network

作者：Zhang, Shengdong[1,2];Zhang, Xiaoqin[1];Wan, Shaohua[3];Ren, Wenqi[4];Zhao, Liping[2];Shen, Linlin[5]

机构：[1]Wenzhou Univ, Key Lab Intelligent Informat Safety & Emergency Zh, Wenzhou 325035, Peoples R China;[2]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China;[3]Univ Elect Sci & Technol China, Shenzhen Inst Adv Study, Shenzhen 518110, Peoples R China;[4]Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen 518107, Peoples R China;[5]Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China

年份：2023

起止页码：1

外文期刊名：IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS

收录：SCI-EXPANDED(收录号：WOS:001085334900001)、、EI(收录号：20234314969417)、Scopus(收录号：2-s2.0-85174799899)、WOS

基金：This work was supported in part by the National Natural Science Foundation of China under Grant U2033210,Grant 82261138629, and Grant 62271321, in part by the Zhejiang Provincial Natural Science Foundation under Grant LDT23F02024F02,in part by the Science and Technology Plan Project in Basic Public Welfare Class of Shaoxing City under Grant 2022A11002, in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2023A1515010688, and in part by the Shenzhen Municipal Science and Technology Innovation Council under Grant JCYJ20220531101412030.Paper no. TII-23-2279.(Corresponding author: Xiaoqin Zhang.)

语种：英文

外文关键词：Dehazing; domain shift; generative adversarial; natural haze images; self-supervised; visual Internet of Things (IoT)

外文摘要：Owing to the fast developments of economics, a lot of devices and objects have been connected and have formed the Internet of Things (IoT). Visual sensors have been applied in vehicle navigation, traffic situational awareness, and traffic safety management. However, the particles in the air degrade the imaging quality, which affects the performance of vehicle navigation, traffic situational awareness, and traffic safety management. Deep-learning-based dehazing methods were proposed to address this issue. However, these methods are trained with simulated hazy images and cannot generalize to natural haze images well. To address the domain shift problem, some methods resort to zero-shot learning or domain adaption to boost the generalization of the model on natural haze images. However, the relevance between dehazed results and clean images is ignored by zero-shot dehazing methods. Domain-adaption-based dehazing methods ignore the relationship between the dehazed results and the hazy images. To overcome these issues, a generative adversarial and self-supervised dehazing network is introduced to boost the dehazing performance on real haze images. First, generative adversarial is employed to construct the relevance between dehazed results and haze-free images, which can boost the natural appearance of dehazed results. Second, self-supervised learning is employed to construct the relevance between the dehazed results and hazy images, which can restrict the solution space of dehazing. To show the effectiveness of the proposed model, we conduct extensive experiments on real and simulated haze images. Compared with state-of-the-art methods, the proposed model achieves state-of-the-art dehazing performance.