{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:33:09Z","timestamp":1777703589217,"version":"3.51.4"},"reference-count":42,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T00:00:00Z","timestamp":1562112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,9,9]]},"abstract":"<jats:p>\u00a0Image denoising is a hot topic in many research fields, such as image processing and computer vision. With the development of deep learning, deep neural networks are widely used for image denoising and have achieved good effectiveness. Inspired by the characteristics of feed-forward denoising convolutional neural network (DnCNN) and biological neuron response, we propose a Symmetry-Rectifier Linear Unit (SyReLU) and further offer a\u00a0corresponding SyReLU activation function, which has a better consistency with biological neuron characteristics in comparison with other activation functions, e.g. Rectifier Linear Unit (ReLU) and Leaky Rectifier Linear Unit(LReLU). Also, in order to denoise image, we use SyReLU activation function for residual learning of CNN (e.g. DnCNN). Specially, the experimental results indicate DnCNN with SyReLU can achieve better effectiveness than DnCNN with other activation functions (e.g.ReLU and LReLU) for image denosing on Set12 and BSD68 datasets. Briefly, the proposed method plays an important role in the development of activation function and is very useful in deep neural networks for image denosing.<\/jats:p>","DOI":"10.3233\/jifs-190017","type":"journal-article","created":{"date-parts":[[2019,7,5]],"date-time":"2019-07-05T10:54:44Z","timestamp":1562324084000},"page":"2809-2818","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":14,"title":["Residual learning of deep convolutional neural networks for image denoising"],"prefix":"10.1177","volume":"37","author":[{"given":"Chuanhui","family":"Shan","sequence":"first","affiliation":[{"name":"College of Computer Science, Beijing University of Technology, Beijing, China"}]},{"given":"Xirong","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Management, Chengdu University of Information Technology, Chengdu, China"}]},{"given":"Jun","family":"Ou","sequence":"additional","affiliation":[{"name":"College of Computer Science, Beijing University of Technology, Beijing, China"}]}],"member":"179","published-online":{"date-parts":[[2019,7,3]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"60","article-title":"A non-local algorithm for image denoising","volume":"2","author":"Buades A.","year":"2005","unstructured":"BuadesA., CollB. and MorelJ.-M., A non-local algorithm for image denoising, IEEE Conference on Computer Vision and Pattern Recognition 2 (2005), 60\u201365.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.901238"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0052-1"},{"key":"e_1_3_1_5_2","first-page":"2272","article-title":"Non-local sparse models for image restoration","author":"Mairal J.","year":"2009","unstructured":"MairalJ., BachF., PonceJ., SapiroG. and ZissermanA., Non-local sparse models for image restoration, IEEE International Conference on Computer Vision, 2009, pp. 2272\u20132279.","journal-title":"IEEE International Conference on Computer Vision"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881969"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2235847"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1137\/040605412"},{"key":"e_1_3_1_10_2","first-page":"1","article-title":"What makes a good model of natural images?","author":"Weiss Y.","year":"2007","unstructured":"WeissY. and FreemanW.T., What makes a good model of natural images? IEEE Conference on Computer Vision and Pattern Recognition, 2007, pp. 1\u20138.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_11_2","first-page":"269","article-title":"Efficient belief propagation with learned higher-order Markov random fields","author":"Lan X.","year":"2006","unstructured":"LanX., RothS., HuttenlocherD. and BlackM.J., Efficient belief propagation with learned higher-order Markov random fields, European Conference on Computer Vision, 2006, pp. 269\u2013282.","journal-title":"European Conference on Computer Vision"},{"key":"e_1_3_1_12_2","volume-title":"Markov random field modeling in image analysis","author":"Li S.Z.","year":"2009","unstructured":"LiS.Z., Markov random field modeling in image analysis, Springer Science & Business Media, 2009."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0197-6"},{"key":"e_1_3_1_14_2","first-page":"2862","article-title":"Weighted nuclear norm minimization with application to image denoising","author":"Gu S.","year":"2014","unstructured":"GuS., ZhangL., ZuoW. and FengX., Weighted nuclear norm minimization with application to image denoising, IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 2862\u20132869.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_15_2","first-page":"2774","article-title":"Shrinkage fields for effective image restoration","author":"Schmidt U.","year":"2014","unstructured":"SchmidtU. and RothS., Shrinkage fields for effective image restoration, IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 2774\u20132781.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_16_2","first-page":"5261","article-title":"On learning optimized reaction diffusion processes for effective image restoration","author":"Chen Y.","year":"2015","unstructured":"ChenY., YuW. and PockT., On learning optimized reaction diffusion processes for effective image restoration, IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5261\u20135269.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_17_2","article-title":"Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration","author":"Chen Y.","year":"2016","unstructured":"ChenY. and PockT., Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration, IEEE transactions on Pattern Analysis and Machine Intelligence, 2016.","journal-title":"IEEE transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_18_2","first-page":"604","article-title":"Discriminative non-blind deblurring","author":"Schmidt U.","year":"2013","unstructured":"SchmidtU., RotherC., NowozinS., JancsaryJ. and RothS., Discriminative non-blind deblurring, IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 604\u2013611.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"issue":"4","key":"e_1_3_1_19_2","first-page":"677","article-title":"Cascades of regression tree fields for image restoration","volume":"38","author":"Schmidt U.","year":"2016","unstructured":"SchmidtU., JancsaryJ., NowozinS., RothS. and RotherC., Cascades of regression tree fields for image restoration, IEEE Conference on Computer Vision and Pattern Recognition 38(4) (2016), 677\u2013689.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_20_2","first-page":"769","article-title":"Natural image denoising with convolutional networks","author":"Jain V.","year":"2009","unstructured":"JainV. and SeungS., Natural image denoising with convolutional networks, Advances in Neural Information Processing Systems, 2009, pp. 769\u2013776.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_21_2","first-page":"2392","article-title":"Image denoising: Can plain neural networks compete with BM3D?","author":"Burger H.C.","year":"2012","unstructured":"BurgerH.C., SchulerC.J. and HarmelingS., Image denoising: Can plain neural networks compete with BM3D? IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2392\u20132399.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_22_2","first-page":"341","article-title":"Image denoising and inpainting with deep neural networks","author":"Xie J.","year":"2012","unstructured":"XieJ., XuL. and ChenE., Image denoising and inpainting with deep neural networks, Advances in Neural Information Processing Systems (2012), 341\u2013349.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_3_1_24_2","article-title":"Deep sparse rectifier neural networks","author":"Glorot X.","year":"2011","unstructured":"GlorotX., BordesA. and BengioY., Deep sparse rectifier neural networks, Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011.","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"issue":"1","key":"e_1_3_1_25_2","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"Maas A.L.","year":"2013","unstructured":"MaasA.L., HannunA.Y. and NgA.Y., Rectifier nonlinearities improve neural network acoustic models, Proc Icml 30(1) (2013), 3\u20138.","journal-title":"Proc Icml"},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. et al. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification Proceedings of the IEEE International Conference on Computer Vision 2015 pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_1_27_2","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"Clevert D.A.","year":"2015","unstructured":"ClevertD.A., UnterthinerT. and HochreiterS., Fast and accurate deep network learning by exponential linear units (elus), ICLR, 2015.","journal-title":"ICLR"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10287"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.01.084"},{"key":"e_1_3_1_30_2","unstructured":"NichollsJ.G. MartinA.R. FuchsP.A. BrownD.A. DiamondM.E. and WeisblatD.A. From neuron to brain Sunderland MA: Sinauer Associates 2012 5th edition."},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1979.sp012686"},{"key":"e_1_3_1_32_2","unstructured":"AdrianE.D. The Physical Background of Perception Clarendon Oxford England 1946."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1097\/00004647-200110000-00001"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0960-9822(03)00135-0"},{"key":"e_1_3_1_35_2","first-page":"3059","volume-title":"International Conference on International Conference on Machine Learning","author":"Gulcehre C.","year":"2016","unstructured":"GulcehreC., MoczulskiM., DenilM. and BengioY., Noisy activation functions, International Conference on International Conference on Machine Learning, JMLR.org, 2016, pp. 3059\u20133068."},{"key":"e_1_3_1_36_2","first-page":"448","volume-title":"International Conference on International Conference on Machine Learning","author":"Ioffe S.","year":"2015","unstructured":"IoffeS. and SzegedyC., Batch normalization: Accelerating deep network training by reducing internal covariate shift, International Conference on International Conference on Machine Learning, JMLR.org, 2015, pp. 448\u2013456."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-18425"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-016-2656-2"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.04.003"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2740400"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2009.2029569"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-172097"},{"key":"e_1_3_1_43_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma D.","year":"2015","unstructured":"KingmaD. and BaJ., Adam: A method for stochastic optimization, International Conference for Learning Representations, 2015.","journal-title":"International Conference for Learning Representations"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-190017","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-190017","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-190017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:39:03Z","timestamp":1777455543000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-190017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,3]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,9,9]]}},"alternative-id":["10.3233\/JIFS-190017"],"URL":"https:\/\/doi.org\/10.3233\/jifs-190017","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,3]]}}}