{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:05:19Z","timestamp":1779692719045,"version":"3.53.1"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108794","type":"journal-article","created":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T15:00:28Z","timestamp":1772377228000},"page":"108794","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Freezing pre-trained parameters of encoders for denoisers: Expanding pixel involvement and filtering out high-frequency noise"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8355-832X","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9037-0122","authenticated-orcid":false,"given":"Junda","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1079-4537","authenticated-orcid":false,"given":"Liang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6463-3603","authenticated-orcid":false,"given":"Beini","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0431-7924","authenticated-orcid":false,"given":"Xiao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3784-7494","authenticated-orcid":false,"given":"Weijia","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108794_bib0001","series-title":"2017\u202fIEEE conference on computer vision and pattern recognition workshops (CVPRW)","first-page":"1122","article-title":"Ntire 2017 challenge on single image super-resolution: Dataset and study","author":"Agustsson","year":"2017"},{"key":"10.1016\/j.neunet.2026.108794_bib0002","series-title":"British machine vision conference","article-title":"Low-complexity single-image super-resolution based on nonnegative neighbor embedding","author":"Bevilacqua","year":"2012"},{"key":"10.1016\/j.neunet.2026.108794_bib0003","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1692","article-title":"Masked image training for generalizable deep image denoising","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.108794_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"25974","article-title":"Transfer CLIP for generalizable image denoising","author":"Cheng","year":"2024"},{"key":"10.1016\/j.neunet.2026.108794_bib0005","unstructured":"del Rio, F., Messina, P., & Dominguez, V. (2018). Do better imagenet models transfer better...for image recommendation?ArXiv, abs\/1807.09870. https:\/\/api.semanticscholar.org\/CorpusID:50786784."},{"key":"10.1016\/j.neunet.2026.108794_bib0006","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3855","article-title":"Removing rain from single images via a deep detail network","author":"Fu","year":"2017"},{"key":"10.1016\/j.neunet.2026.108794_bib0007","unstructured":"Goodfellow, I. J., Pouget-Abadie, J., & Mirza, M. (2014). Generative adversarial networks. arXiv e-prints, (p. 10.48550\/arXiv.1406.2661."},{"key":"10.1016\/j.neunet.2026.108794_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9199","article-title":"Interpreting super-resolution networks with local attribution maps","author":"Gu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108794_bib0009","unstructured":"Gu, X., Lin, T.-Y., & Kuo, W. (2021). Open-vocabulary object detection via vision and language knowledge distillation. arXiv e-prints, (p. 10.48550\/arXiv.2104.13921."},{"key":"10.1016\/j.neunet.2026.108794_bib0010","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.108794_bib0011","doi-asserted-by":"crossref","unstructured":"Howard, J., & Ruder, S. (2018). Universal language model fine-tuning for text classification. arXiv e-prints, (p. 10.48550\/arXiv.1801.06146.","DOI":"10.18653\/v1\/P18-1031"},{"key":"10.1016\/j.neunet.2026.108794_bib0012","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.neunet.2026.108794_bib0013","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"5197","article-title":"Single image super-resolution from transformed self-exemplars","author":"Huang","year":"2015"},{"key":"10.1016\/j.neunet.2026.108794_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","first-page":"0","article-title":"GRDN: Grouped residual dense network for real image denoising and gan-based real-world noise modeling","author":"Kim","year":"2019"},{"issue":"1","key":"10.1016\/j.neunet.2026.108794_bib0015","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":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108794_bib0016","unstructured":"Li, B., Weinberger, K. Q., & Belongie, S. J. (2022a). Language-driven semantic segmentation. ArXiv, abs\/2201.03546. https:\/\/api.semanticscholar.org\/CorpusID:245836975."},{"key":"10.1016\/j.neunet.2026.108794_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10965","article-title":"Grounded language-image pre-training","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108794_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1714","article-title":"Learning distortion invariant representation for image restoration from a causality perspective","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.108794_bib0019","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition workshops","first-page":"136","article-title":"Enhanced deep residual networks for single image super-resolution","author":"Lim","year":"2017"},{"key":"10.1016\/j.neunet.2026.108794_bib0020","unstructured":"Liu, Y., Liu, A., & Gu, J. (2021). Discovering distinctive \u201csemantics\u201d in super-resolution networks. arXiv preprint arXiv: 2108.00406."},{"key":"10.1016\/j.neunet.2026.108794_bib0021","article-title":"In-vitro blood purification using tiny pinch holographic optical tweezers based on deep learning","author":"Luo","year":"2024","journal-title":"Biosensors and Bioelectronics"},{"issue":"8","key":"10.1016\/j.neunet.2026.108794_bib0022","doi-asserted-by":"crossref","DOI":"10.3390\/s24082583","article-title":"Real-time 3d tracking of multi-particle in the wide-field illumination based on deep learning","volume":"24","author":"Luo","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.108794_bib0023","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.108794_bib0024","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional neural networks for medical image analysis: Full training or fine tuning?","volume":"35","author":"Tajbakhsh","year":"2016","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.neunet.2026.108794_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.106949","article-title":"Designing and training of a dual CNN for image denoising","volume":"226","author":"Tian","year":"2021","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108794_bib0026","series-title":"Proceedings of the asian conference on computer vision","article-title":"GAN-based noise model for denoising real images","author":"Tran","year":"2020"},{"key":"10.1016\/j.neunet.2026.108794_bib0027","series-title":"Neural information processing systems","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2026.108794_bib0028","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.ins.2021.04.045","article-title":"HI-GAN: A hierarchical generative adversarial network for blind denoising of real photographs","volume":"570","author":"Vo","year":"2021","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2026.108794_bib0029","series-title":"2021\u202fIEEE\/CVF international conference on computer vision workshops (ICCVW)","first-page":"1905","article-title":"Real-ESRGAN: Training real-world blind super-resolution with pure synthetic data","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108794_bib0030","series-title":"2016\u202fIEEE conference on computer vision and pattern recognition (CVPR)","first-page":"4810","article-title":"Event-specific image importance","author":"Wang","year":"2016"},{"key":"10.1016\/j.neunet.2026.108794_bib0031","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"17683","article-title":"Uformer: A general u-shaped transformer for image restoration","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108794_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16133","article-title":"ConvNext v2: Co-designing and scaling convnets with masked autoencoders","author":"Woo","year":"2023"},{"key":"10.1016\/j.neunet.2026.108794_bib0033","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7959","article-title":"Robust fine-tuning of zero-shot models","author":"Wortsman","year":"2022"},{"key":"10.1016\/j.neunet.2026.108794_bib0034","doi-asserted-by":"crossref","first-page":"798","DOI":"10.1016\/j.apm.2023.10.023","article-title":"Wavelet analysis model inspired convolutional neural networks for image denoising","volume":"125","author":"Xu","year":"2024","journal-title":"Applied Mathematical Modelling"},{"key":"10.1016\/j.neunet.2026.108794_bib0035","series-title":"International joint conference on artificial intelligence","article-title":"Towards adversarially robust deep image denoising","author":"Yan","year":"2022"},{"key":"10.1016\/j.neunet.2026.108794_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5728","article-title":"Restormer: Efficient transformer for high-resolution image restoration","author":"Zamir","year":"2022"},{"key":"10.1016\/j.neunet.2026.108794_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14821","article-title":"Multi-stage progressive image restoration","author":"Zamir","year":"2021"},{"key":"10.1016\/j.neunet.2026.108794_bib0038","series-title":"Curves and surfaces: 7th international conference, Avignon, France, June 24-30, 2010, revised selected papers 7","first-page":"711","article-title":"On single image scale-up using sparse-representations","author":"Zeyde","year":"2012"},{"key":"10.1016\/j.neunet.2026.108794_bib0039","series-title":"GLIPv2: Unifying localization and vision-language understanding","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108794_bib0040","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1007\/s11633-023-1466-0","article-title":"Practical blind image denoising via swin-conv-UNet and data synthesis","volume":"20","author":"Zhang","year":"2022","journal-title":"Machine Intelligence Research"},{"issue":"7","key":"10.1016\/j.neunet.2026.108794_bib0041","doi-asserted-by":"crossref","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","article-title":"Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108794_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11710","article-title":"A poisson-Gaussian denoising dataset with real fluorescence microscopy images","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neunet.2026.108794_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7982","article-title":"Image super-resolution by neural texture transfer","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neunet.2026.108794_bib0044","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7340","article-title":"Fine-tuning convolutional neural networks for biomedical image analysis: Actively and incrementally","author":"Zhou","year":"2017"},{"issue":"C","key":"10.1016\/j.neunet.2026.108794_bib0045","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.neunet.2023.08.056","article-title":"Single image denoising with a feature-enhanced network","volume":"168","author":"Zhuge","year":"2023","journal-title":"Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600256X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600256X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:37:49Z","timestamp":1779691069000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802600256X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":45,"alternative-id":["S089360802600256X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108794","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Freezing pre-trained parameters of encoders for denoisers: Expanding pixel involvement and filtering out high-frequency noise","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108794","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108794"}}