Semi-supervised image dehazing algorithm based on teacher-student learning

doi:10.11772/j.issn.1001-9081.2024091382

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (9): 2975-2983.DOI: 10.11772/j.issn.1001-9081.2024091382

• Multimedia computing and computer simulation • Previous Articles

Semi-supervised image dehazing algorithm based on teacher-student learning

Panfeng JING¹, Yudong LIANG¹^,²(), Chaowei LI³, Junru GUO¹, Jinyu GUO¹

^1.School of Computer and Information Technology，Shanxi University，Taiyuan Shanxi 030006，China
^2.Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education （Shanxi University），Taiyuan Shanxi 030006，China
^3.Jingying Shuzhi Technology Company Limited，Taiyuan Shanxi 030012，China

Received:2024-09-27 Revised:2025-01-07 Accepted:2025-01-13 Online:2025-03-17 Published:2025-09-10
Contact: Yudong LIANG
About author:JING Panfeng， born in 1999， M. S. candidate. His research interests include computer vision， image processing.
LI Chaowei， born in 1987， M. S. His research interests include computer vision， intelligent coal mining.
GUO Junru， born in 1999， M. S. candidate. Her research interests include computer vision， image processing.
GUO Jinyu， born in 2002， M. S. candidate. His research interests include computer vision， image processing.
Supported by:
National Natural Science Foundation of China(61802237);Fundamental Research Program of Shanxi Province(202203021221002);Natural Science Foundation of Shanxi Province(201901D211176);Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi(2019L0066);Science and Technology Major Project of Shanxi Province(202101020101019);Key Research and Development Program of Shanxi Province(202102070301019);Special Fund for Science and Technology Innovation Teams of Shanxi(202204051001015)

基于师生学习的半监督图像去雾算法

景攀峰¹, 梁宇栋¹^,²(), 李超伟³, 郭俊茹¹, 郭晋育¹

^1.山西大学计算机与信息技术学院，太原 030006
^2.计算智能与中文信息处理教育部重点实验室（山西大学），太原 030006
^3.精英数智科技股份有限公司，太原 030012

通讯作者: 梁宇栋
作者简介:景攀峰（1999—），男，山西运城人，硕士研究生，主要研究方向：计算机视觉、图像处理
李超伟（1987—），男，山西吕梁人，硕士，主要研究方向：计算机视觉、煤矿智能化
郭俊茹（1999—），女，山西运城人，硕士研究生，主要研究方向：计算机视觉、图像处理
郭晋育（2002—），男，山西吕梁人，硕士研究生，主要研究方向：计算机视觉、图像处理。
基金资助:
国家自然科学基金资助项目(61802237);国家自然科学基金资助项目(62272284);山西省基础研究计划项目(202203021221002);山西省基础研究计划项目(202203021211291);山西省自然科学基金资助项目(201901D211176);山西省自然科学基金资助项目(202103021223464);山西省高等学校科技创新项目(2019L0066);山西省科技重大专项(202101020101019);山西省重点研发计划项目(202102070301019);山西省科技创新人才团队专项(202204051001015)

Abstract

Abstract:

Image dehazing is a hot topic in the field of computer vision. Acquiring large-scale， high-quality paired datasets from real world is costly and challenging. Consequently， existing methods use synthetic data for fully supervised deep learning model training， may lead to poor real-world performance of the model. To bridge the domain gap between synthetic and real domains， a semi-supervised image dehazing algorithm based on teacher-student learning was introduced. In this algorithm， a semi-supervised teacher-student learning with Exponential Moving Average （EMA） strategy was used to update the teacher model， and an end-to-end dehazing learning was performed， thereby addressing domain shift issues between synthetic and real data significantly and enhancing generalization performance of the model in real hazy scenarios. Experimental results demonstrate that the proposed algorithm achieves superior performance on two synthetic hazy image datasets SOTS （Synthetic Objective Testing Set） and Haze4K， as well as the real-world hazy image dataset URHI （Unannotated Real-world Hazy Images）， while also delivering enhanced dehazing visual effects.

Key words: image dehazing, deep learning, semi-supervised learning, teacher-student learning, domain difference

摘要：

图像去雾是计算机视觉领域的热点话题之一。由于真实世界中大规模高质量的配对数据集的获取存在成本昂贵、实施困难等问题，现有方法通常利用合成数据对深度学习模型进行全监督训练，这可能会导致模型在真实场景下的泛化性能较差。为了解决真实域和合成域之间的域差异问题，提出一种基于师生学习的半监督图像去雾算法。该算法采用一个半监督的师生学习框架，利用指数移动平均（EMA）策略来更新教师模型，并端到端地进行去雾学习，显著地解决了合成数据与真实数据之间的域偏移问题，并提高了模型在真实有雾场景下的泛化性能。实验结果表明，所提算法在2个合成雾霾图像数据集SOTS（Synthetic Objective Testing Set）、Haze4K和真实雾霾图像数据集URHI（Unannotated Real-world Hazy Images）上取得了较好性能，并获得了更好的去雾视觉效果。

关键词: 图像去雾, 深度学习, 半监督学习, 师生学习, 域差异

CLC Number:

TP391

Panfeng JING, Yudong LIANG, Chaowei LI, Junru GUO, Jinyu GUO. Semi-supervised image dehazing algorithm based on teacher-student learning[J]. Journal of Computer Applications, 2025, 45(9): 2975-2983.

景攀峰, 梁宇栋, 李超伟, 郭俊茹, 郭晋育. 基于师生学习的半监督图像去雾算法[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2975-2983.

Figures/Tables 8

References 35

[1]	XIONG Y， LI Z， CHEN Y， et al. Efficient deformable ConvNets： rethinking dynamic and sparse operator for vision applications ［C］// Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2024： 5652-5661.
[2]	XIAO D， MENG Q， LI S， et al. Improving Transformers with dynamically composable multi-head attention ［C］// Proceedings of the 41st International Conference on Machine Learning. New York： JMLR.org， 2024： 54300-54318.
[3]	KIM T K， PAIK J K， KANG B S. Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering ［J］. IEEE Transactions on Consumer Electronics， 1998， 44（1）： 82-87.
[4]	FAN Y， ZHANG L， GUO H， et al. Image processing for laser imaging using adaptive homomorphic filtering and total variation［J］. Photonics， 2020， 7（2）： No.30.
[5]	DAUBECHIES I. The wavelet transform， time-frequency localization and signal analysis ［J］. IEEE Transactions on Information Theory， 1990， 36（5）： 961-1005.
[6]	RAHMAN Z U， JOBSON D J， WOODELL G A. Retinex processing for automatic image enhancement ［J］. Journal of Electronic Imaging， 2004， 13（1）： No.1636183.
[7]	NARASIMHAN S G， NAYAR S K. Chromatic framework for vision in bad weather ［C］// Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition — Volume 1. Piscataway： IEEE， 2000： 598-605.
[8]	NARASIMHAN S G， NAYAR S K. Vision and the atmosphere ［J］. International Journal of Computer Vision， 2002， 48（3）： 233-254.
[9]	TAN R T. Visibility in bad weather from a single image ［C］// Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2008： 1-8.
[10]	FATTAL R. Single image dehazing ［J］. ACM Transactions on Graphics， 2008， 27（3）： No.72.
[11]	HE K， SUN J， TANG X. Single image haze removal using dark channel prior ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2011， 33（12）： 2341-2353.
[12]	CAI B， XU X， JIA K， et al. DehazeNet： an end-to-end system for single image haze removal ［J］. IEEE Transactions on Image Processing， 2016， 25（11）： 5187-5198.
[13]	LI B， PENG X， WANG Z， et al. An all-in-one network for dehazing and beyond ［EB/OL］. ［2024-01-14］. .
[14]	LIU X， MA Y， SHI Z， et al. GridDehazeNet： attention-based multi-scale network for image dehazing ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 7313-7322.
[15]	QIN X， WANG Z， BAI Y， et al. FFA-Net： feature fusion attention network for single image dehazing ［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2020： 11908-11915.
[16]	DONG H， PAN J， XIANG L， et al. Multi-scale boosted dehazing network with dense feature fusion ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 2154-2164.
[17]	WU H， QU Y， LIN S， et al. Contrastive learning for compact single image dehazing ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 10546-10555.
[18]	LIU Y， ZHU L， PEI S， et al. From synthetic to real： image dehazing collaborating with unlabeled real data ［C］// Proceedings of the 29th ACM International Conference on Multimedia. New York： ACM， 2021： 50-58.
[19]	SONG Y， HE Z， QIAN H， et al. Vision Transformers for single image dehazing ［J］. IEEE Transactions on Image Processing， 2023， 32： 1927-1941.
[20]	LU L， XIONG Q， XU B， et al. MixDehazeNet： mix structure block for image dehazing network ［C］// Proceedings of the 2024 International Joint Conference on Neural Networks. Piscataway： IEEE， 2024： 1-10.
[21]	CUI Y， REN W， CAO X， et al. Image restoration via frequency selection ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2024， 46（2）： 1093-1108.
[22]	CUI Y， REN W， CAO X， et al. Revitalizing convolutional network for image restoration ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2024， 46（12）： 9423-9438.
[23]	YANG W， WANG S， FANG Y， et al. From fidelity to perceptual quality： a semi-supervised approach for low-light image enhancement ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 3060-3069.
[24]	YASARLA R， SINDAGI V A， PATEL V M. Syn2Real transfer learning for image deraining using Gaussian processes ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 2723-2733.
[25]	SHAO Y， LI L， REN W， et al. Domain adaptation for image dehazing ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 2805-2814.
[26]	YUE Z， XIE J， ZHAO Q， et al. Semi-supervised video deraining with dynamical rain generator ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 642-652.
[27]	HUANG H， YU A， HE R. Memory oriented transfer learning for semi-supervised image deraining ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 7728-7737.
[28]	WANG J， WANG F， YIN D. Feature decoupled autoencoder： semi-supervised learning for image dehazing ［C］// Proceedings of the 2022 IEEE International Conference on Multimedia and Expo. Piscataway： IEEE， 2022： 1-6.
[29]	SUN Z， ZHANG Y， BAO F， et al. SADnet： semi-supervised single image dehazing method based on an attention mechanism［J］. ACM Transactions on Multimedia Computing， Communications， and Applications， 2022， 18（2）： No.58.
[30]	YASARLA R， PRIEBE C E， PATEL V M. ART-SS： an adaptive rejection technique for semi-supervised restoration for adverse weather-affected images ［C］// Proceedings of the 2022 European Conference on Computer Vision， LNCS 13678. Cham： Springer， 2022： 699-718.
[31]	CUI X， WANG C， REN D， et al. Semi-supervised image deraining using knowledge distillation ［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2022， 32（12）： 8327-8341.
[32]	DONG Y， LI Y， DONG Q， et al. Semi-supervised domain alignment learning for single image dehazing ［J］. IEEE Transactions on Cybernetics， 2023， 53（11）： 7238-7250.
[33]	LIU Y， YAN Z， CHEN S， et al. NightHazeFormer： single nighttime haze removal using prior query Transformer ［C］// Proceedings of the 31st ACM International Conference on Multimedia. New York： ACM， 2023： 4119-4128.
[34]	LI B， REN W， FU D， et al. Benchmarking single-image dehazing and beyond ［J］. IEEE Transactions on Image Processing， 2019， 28（1）： 492-505.
[35]	KINGMA D P， BA J L. Adam： a method for stochastic optimization ［EB/OL］. ［2024-07-05］..

算法	年份	PSNR/dB	SSIM
DCP^［11］	2011	18.250 4	0.853 2
DehazeNet^［12］	2016	18.144 2	0.561 4
AOD-Net^［13］	2017	20.600 3	0.858 7
GridDehazeNet^［14］	2019	25.704 1	0.931 8
FFA-Net^［15］	2020	27.198 4	0.948 2
MSBDN^［16］	2020	27.137 3	0.951 7
AECR-Net^［17］	2021	27.904 0	0.935 6
DehazeFormer^［19］	2023	30.444 2	0.968 4
MixDehazeNet^［20］	2023	29.870 8	0.961 3
FSNet^［21］	2024	31.271 2	0.972 6
ConvIR^［22］	2024	30.823 6	0.964 7
本文算法	2024	31.031 2	0.968 0

算法	年份	PSNR/dB	SSIM
DCP^［11］	2011	18.250 4	0.853 2
DehazeNet^［12］	2016	18.144 2	0.561 4
AOD-Net^［13］	2017	20.600 3	0.858 7
GridDehazeNet^［14］	2019	25.704 1	0.931 8
FFA-Net^［15］	2020	27.198 4	0.948 2
MSBDN^［16］	2020	27.137 3	0.951 7
AECR-Net^［17］	2021	27.904 0	0.935 6
DehazeFormer^［19］	2023	30.444 2	0.968 4
MixDehazeNet^［20］	2023	29.870 8	0.961 3
FSNet^［21］	2024	31.271 2	0.972 6
ConvIR^［22］	2024	30.823 6	0.964 7
本文算法	2024	31.031 2	0.968 0

算法	年份	PSNR/dB	SSIM
DCP^［11］	2011	16.926 5	0.858 2
DehazeNet^［12］	2016	15.600 5	0.534 2
AOD-Net^［13］	2017	17.871 3	0.821 9
GridDehazeNet^［14］	2019	21.185 4	0.900 1
FFA-Net^［15］	2020	22.109 3	0.921 8
MSBDN^［16］	2020	22.932 1	0.928 9
AECR-Net^［17］	2021	22.421 5	0.927 6
DehazeFormer^［19］	2023	24.178 2	0.946 0
MixDehazeNet^［20］	2023	23.016 1	0.935 3
FSNet^［21］	2024	23.587 0	0.947 1
ConvIR^［22］	2024	23.236 5	0.942 0
本文算法	2024	25.130 6	0.951 5

算法	年份	PSNR/dB	SSIM
DCP^［11］	2011	16.926 5	0.858 2
DehazeNet^［12］	2016	15.600 5	0.534 2
AOD-Net^［13］	2017	17.871 3	0.821 9
GridDehazeNet^［14］	2019	21.185 4	0.900 1
FFA-Net^［15］	2020	22.109 3	0.921 8
MSBDN^［16］	2020	22.932 1	0.928 9
AECR-Net^［17］	2021	22.421 5	0.927 6
DehazeFormer^［19］	2023	24.178 2	0.946 0
MixDehazeNet^［20］	2023	23.016 1	0.935 3
FSNet^［21］	2024	23.587 0	0.947 1
ConvIR^［22］	2024	23.236 5	0.942 0
本文算法	2024	25.130 6	0.951 5

模块	PSNR/dB	SSIM
Baseline	29.789 1	0.965 7
Baseline+PCSAB	30.609 9	0.966 2
Baseline+师生学习	30.259 2	0.963 9
Baseline+PCSAB+师生学习	31.032 1	0.968 0

Semi-supervised image dehazing algorithm based on teacher-student learning

基于师生学习的半监督图像去雾算法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 35

Related Articles 15

Recommended Articles

Metrics

[1]	Hongjun ZHANG, Gaojun PAN, Hao YE, Yubin LU, Yiheng MIAO. Multi-source heterogeneous data analysis method combining deep learning and tensor decomposition [J]. Journal of Computer Applications, 2025, 45(9): 2838-2847.
[2]	Jin LI, Liqun LIU. SAR and visible image fusion based on residual Swin Transformer [J]. Journal of Computer Applications, 2025, 45(9): 2949-2956.
[3]	Bing YIN, Zhenhua LING, Yin LIN, Changfeng XI, Ying LIU. Emotion recognition method compatible with missing modal reasoning [J]. Journal of Computer Applications, 2025, 45(9): 2764-2772.
[4]	Lina GE, Mingyu WANG, Lei TIAN. Review of research on efficiency of federated learning [J]. Journal of Computer Applications, 2025, 45(8): 2387-2398.
[5]	Yanhua LIAO, Yuanxia YAN, Wenlin PAN. Multi-target detection algorithm for traffic intersection images based on YOLOv9 [J]. Journal of Computer Applications, 2025, 45(8): 2555-2565.
[6]	Peng PENG, Ziting CAI, Wenling LIU, Caihua CHEN, Wei ZENG, Baolai HUANG. Speech emotion recognition method based on hybrid Siamese network with CNN and bidirectional GRU [J]. Journal of Computer Applications, 2025, 45(8): 2515-2521.
[7]	Shuo ZHANG, Guokai SUN, Yuan ZHUANG, Xiaoyu FENG, Jingzhi WANG. Dynamic detection method of eclipse attacks for blockchain node analysis [J]. Journal of Computer Applications, 2025, 45(8): 2428-2436.
[8]	Jinxian SUO, Liping ZHANG, Sheng YAN, Dongqi WANG, Yawen ZHANG. Review of interpretable deep knowledge tracing methods [J]. Journal of Computer Applications, 2025, 45(7): 2043-2055.
[9]	Zhenzhou WANG, Fangfang GUO, Jingfang SU, He SU, Jianchao WANG. Robustness optimization method of visual model for intelligent inspection [J]. Journal of Computer Applications, 2025, 45(7): 2361-2368.
[10]	Qiaoling QI, Xiaoxiao WANG, Qianqian ZHANG, Peng WANG, Yongfeng DONG. Label noise adaptive learning algorithm based on meta-learning [J]. Journal of Computer Applications, 2025, 45(7): 2113-2122.
[11]	Xiaoyang ZHAO, Xinzheng XU, Zhongnian LI. Research review on explainable artificial intelligence in internet of things applications [J]. Journal of Computer Applications, 2025, 45(7): 2169-2179.
[12]	Tianchen HUA, Xiaoning MA, Hui ZHI. Portable executable malware static detection model based on shallow artificial neural network [J]. Journal of Computer Applications, 2025, 45(6): 1911-1921.
[13]	Lanhao LI, Haojun YAN, Haoyi ZHOU, Qingyun SUN, Jianxin LI. Multi-scale information fusion time series long-term forecasting model based on neural network [J]. Journal of Computer Applications, 2025, 45(6): 1776-1783.
[14]	Dan WANG, Wenhao ZHANG, Lijuan PENG. Channel estimation of reconfigurable intelligent surface assisted communication system based on deep learning [J]. Journal of Computer Applications, 2025, 45(5): 1613-1618.
[15]	Ying TAN, Xinyu REN, Chaoli SUN, Sisi WANG. Two-stage infill sampling-based semi-supervised expensive multi-objective optimization algorithm [J]. Journal of Computer Applications, 2025, 45(5): 1605-1612.