We present an effective semi-supervised learning algorithm for single image dehazing. The proposed algorithm applies a deep Convolutional Neural Network (CNN) containing a supervised learning branch and an unsupervised learning branch. In the supervised branch, the deep neural network is constrained by the supervised loss functions, which are mean squared, perceptual, and adversarial losses. In the unsupervised branch, we exploit the properties of clean images via sparsity of dark channel and gradient priors to constrain the network. We train the proposed network on both the synthetic data and real-world images in an end-To-end manner. Our analysis shows that the proposed semi-supervised learning algorithm is not limited to synthetic training datasets and can be generalized well to real-world images. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-The-Art single image dehazing algorithms on both benchmark datasets and real-world images.
|Number of pages||14|
|Journal||IEEE Transactions on Image Processing|
|Publication status||Published - 2020|
Bibliographical noteFunding Information:
Manuscript received March 13, 2019; revised August 7, 2019 and October 2, 2019; accepted October 23, 2019. Date of publication November 15, 2019; date of current version January 23, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61433007, Grant 61901184, Grant 61872421, and Grant 61922043, in part by the Natural Science Foundation of Jiangsu Province under Grant BK20180471, and in part by the National Science Foundation CAREER under Grant 1149783. The work of W. Ren was supported in part by the CCF-DiDi GAIA (YF20180101) and in part by the Zhejiang Lab’s International Talent Fund for Young Professionals. The work of L. Li was supported in part by the scholarship from the China Scholarship Council. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Xin Li. (Lerenhan Li and Yunlong Dong contributed equally to this work.) (Corresponding author: Nong Sang.) L. Li, Y. Dong, C. Gao, and N. Sang are with the National Key Laboratory of Science and Technology on Multi-spectral Information Processing, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China (e-mail: firstname.lastname@example.org; email@example.com; firstname.lastname@example.org; email@example.com).
© 1992-2012 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design