{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:09:57Z","timestamp":1772554197211,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T00:00:00Z","timestamp":1649808000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["No. JCYJ20200109142612234"],"award-info":[{"award-number":["No. JCYJ20200109142612234"]}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["No. 2021A1515012313"],"award-info":[{"award-number":["No. 2021A1515012313"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Haze can cause a significant reduction in the contrast and brightness of images. CNN-based methods have achieved benign performance on synthetic data. However, they show weak generalization performance on real data because they are only trained on fully labeled data, ignoring the role of natural data in the network. That is, there exists distribution shift. In addition to using little real data for training image dehazing networks in the literature, few studies have designed losses to constrain the intermediate latent space and the output simultaneously. This paper presents a semi-supervised neural process dehazing network with asymmetry pseudo labels. First, we use labeled data to train a backbone network and save intermediate latent features and parameters. Then, in the latent space, the neural process maps the latent features of real data to the latent space of synthetic data to generate one pseudo label. One neural process loss is proposed here. For situations where the image may be darker after dehazing, another pseudo label is created, and one new loss is used to guide the dehazing result at the output end. We combine the two pseudo labels with designed losses to suppress the distribution shift and guide better dehazing results. Finally, the artificial and hazy natural images are tested experimentally to demonstrate the method\u2019s effectiveness.<\/jats:p>","DOI":"10.3390\/sym14040806","type":"journal-article","created":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T00:42:34Z","timestamp":1649810554000},"page":"806","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["SNPD: Semi-Supervised Neural Process Dehazing Network with Asymmetry Pseudo Labels"],"prefix":"10.3390","volume":"14","author":[{"given":"Fan","family":"Zhou","sequence":"first","affiliation":[{"name":"Research Institute of Sun Yat-sen University in Shenzhen, School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou 510006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaozhe","family":"Meng","sequence":"additional","affiliation":[{"name":"Research Institute of Sun Yat-sen University in Shenzhen, School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou 510006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Feng","sequence":"additional","affiliation":[{"name":"Research Institute of Sun Yat-sen University in Shenzhen, School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou 510006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6090-0110","authenticated-orcid":false,"given":"Zhuo","family":"Su","sequence":"additional","affiliation":[{"name":"Research Institute of Sun Yat-sen University in Shenzhen, School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou 510006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, Y., Yang, Y., and Liu, D. (2021, January 20\u201325). PSD: Principled synthetic-to-real dehazing guided by physical priors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00710"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Hassan, H., Mishra, P., Ahmad, M., Bashir, A.K., Huang, B., and Luo, B. (2022). Effects of haze and dehazing on deep learning-based vision models. Appl. Intell., 1\u201319.","DOI":"10.1007\/s10489-022-03245-5"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhao, W., Zhao, Y., Feng, L., and Tang, J. (2022). Attention Optimized Deep Generative Adversarial Network for Removing Uneven Dense Haze. Symmetry, 14.","DOI":"10.3390\/sym14010001"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhu, H., Peng, X., Chandrasekhar, V., Li, L., and Lim, J.H. (2018, January 13\u201319). DehazeGAN: When image dehazing meets differential programming. Proceedings of the International Joint Conferences on Artificial Intelligence Organization, Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/172"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1023\/A:1016328200723","article-title":"Vision and the atmosphere","volume":"48","author":"Narasimhan","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref_6","first-page":"2341","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2651362","article-title":"Dehazing using color-lines","volume":"34","author":"Fattal","year":"2014","journal-title":"ACM Trans. Graph."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Berman, D., Treibitz, T., and Avidan, S. (2016, January 27\u201330). Non-local image dehazing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.185"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5187","DOI":"10.1109\/TIP.2016.2598681","article-title":"Dehazenet: An end-to-end system for single image haze removal","volume":"25","author":"Cai","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, B., Peng, X., Wang, Z., Xu, J., and Feng, D. (2017, January 22\u201329). AOD-net: All-in-one dehazing network. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.511"},{"key":"ref_11","unstructured":"Liu, X., Ma, Y., Shi, Z., and Chen, J. (November, January 27). Griddehazenet: Attention-based multi-scale network for image dehazing. Proceedings of the IEEE International Conference on Computer Vision, Seul, Korea."},{"key":"ref_12","unstructured":"Qin, X., Wang, Z., Bai, Y., Xie, X., and Jia, H. (2020, January 2\u201312). FFA-net: Feature fusion attention network for single image dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, New York, NY, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Vishal, M.P. (2018, January 18\u201322). Densely connected pyramid dehazing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00337"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., and Fergus, R. (2012, January 7\u201313). Indoor segmentation and support inference from RGBD images. Proceedings of the European Conference on Computer Vision, Florence, Italy.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1109\/TIP.2018.2867951","article-title":"Benchmarking single-image dehazing and beyond","volume":"28","author":"Li","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yasarla, R., Sindagi, V.A., and Patel, V.M. (2020, January 14\u201319). Syn2Real transfer learning for image deraining using Gaussian processes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00280"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2766","DOI":"10.1109\/TIP.2019.2952690","article-title":"Semi-supervised image dehazing","volume":"29","author":"Li","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","first-page":"3011","article-title":"Gaussian processes for machine learning (GPML) toolbox","volume":"11","author":"Rasmussen","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3104","DOI":"10.1109\/TIP.2019.2957852","article-title":"IDGCP: Image Dehazing Based on Gamma Correction Prior","volume":"29","author":"Ju","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2212","DOI":"10.1109\/TIP.2018.2823424","article-title":"Contrast in haze removal: Configurable contrast enhancement model based on dark channel prior","volume":"28","author":"Liu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1109\/TIP.2017.2771158","article-title":"Single image dehazing using color ellipsoid prior","volume":"27","author":"Bui","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3522","DOI":"10.1109\/TIP.2015.2446191","article-title":"A fast single image haze removal algorithm using color attenuation prior","volume":"24","author":"Zhu","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., and Yang, M.H. (2016, January 8\u201316). Single image dehazing via multi-scale convolutional neural networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_10"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Dong, H., Pan, J., Xiang, L., Hu, Z., and Zhang, X. (2020, January 14\u201319). Multi-scale boosted dehazing network with dense feature fusion. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00223"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8457","DOI":"10.1109\/TIP.2020.3016134","article-title":"Zero-shot image dehazing","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Qu, Y., Chen, Y., Huang, J., and Xie, Y. (2019, January 16\u201320). Enhanced pix2pix dehazing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00835"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3211","DOI":"10.1109\/TCSVT.2018.2880223","article-title":"Visual haze removal by a unified generative adversarial network","volume":"29","author":"Pang","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2449","DOI":"10.1109\/TPAMI.2020.2969348","article-title":"Physics-based generative adversarial models for image restoration and beyond","volume":"43","author":"Pan","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1109\/TIP.2019.2952032","article-title":"Unsupervised single image dehazing using dark channel prior loss","volume":"29","author":"Golts","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Pang, Y., Nie, J., Xie, J., Han, J., and Li, X. (2020, January 14\u201319). BidNet: Binocular image dehazing without explicit disparity estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00597"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wu, H., Qu, Y., Lin, S., Zhou, J., Qiao, R., Zhang, Z., Xie, Y., and Ma, L. (2021, January 20\u201315). Contrastive learning for compact single image dehazing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, X., Dong, H., Pan, J., Zhu, C., Tai, Y., Wang, C., Li, J., Huang, F., and Wang, F. (2021, January 20\u201325). Learning to restore hazy video: A new real-world dataset and a new method. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00912"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wei, W., Meng, D., Zhao, Q., Xu, Z., and Wu, Y. (2019, January 15\u201320). Semi-supervised transfer learning for image rain removal. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00400"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_35","unstructured":"Lee, D.H. (2013, January 16\u201321). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. Proceedings of the International Conference on Machine Learning (ICML 2013), Atlanta, GA, USA."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Shao, Y., Li, L., Ren, W., Gao, C., and Sang, N. (2020, January 14\u201319). Domain adaptation for image dehazing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00288"},{"key":"ref_37","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2599","DOI":"10.1109\/TPAMI.2018.2865304","article-title":"Fast and accurate image super-resolution with deep laplacian pyramid networks","volume":"41","author":"Lai","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., and Fei-Fei, L. (2016, January 8\u201316). Perceptual losses for real-time style transfer and super-resolution. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref_40","unstructured":"Garnelo, M., Rosenbaum, D., Maddison, C., Ramalho, T., Saxton, D., Shanahan, M., Teh, Y.W., Rezende, D., and Eslami, S.A. (2018, January 10\u201315). Conditional neural processes. Proceedings of the International Conference on Machine Learning PMLR, Stockholm, Sweden."},{"key":"ref_41","unstructured":"Garnelo, M., Schwarz, J., Rosenbaum, D., Viola, F., Rezende, D.J., Eslami, S., and Teh, Y.W. (2018). Neural processes. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational Inference: A Review for Statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Yang, D., and Sun, J. (2018, January 8\u201314). Proximal dehaze-net: A prior learning-based deep network for single image dehazing. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_43"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a completely blind image quality analyzer","volume":"20","author":"Mittal","year":"2012","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-reference image quality assessment in the spatial domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"ref_46","unstructured":"Crete, F., Dolmiere, T., Ladret, P., and Nicolas, M. (February, January 29). The blur effect: Perception and estimation with a new no-reference perceptual blur metric. Proceedings of the Human Vision and Electronic Imaging XII SPIE, San Jose, CA, USA."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"3998","DOI":"10.1109\/TIP.2018.2831899","article-title":"NIMA: Neural image assessment","volume":"27","author":"Talebi","year":"2018","journal-title":"IEEE Trans. Image Process."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/4\/806\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:52:53Z","timestamp":1760136773000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/4\/806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,13]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["sym14040806"],"URL":"https:\/\/doi.org\/10.3390\/sym14040806","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,13]]}}}