{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T20:59:59Z","timestamp":1754600399034,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"DST, MST, GoI","award":["T-319"],"award-info":[{"award-number":["T-319"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16159-2","type":"journal-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T08:03:23Z","timestamp":1689926603000},"page":"18497-18536","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Revisiting activation functions: empirical evaluation for image understanding and classification"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7053-1654","authenticated-orcid":false,"given":"Shradha","family":"Verma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2763-2839","authenticated-orcid":false,"given":"Anuradha","family":"Chug","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8675-6903","authenticated-orcid":false,"given":"Amit Prakash","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,21]]},"reference":[{"key":"16159_CR1","unstructured":"Ahmad M, Khan AM, Mazzara M, Distefano S, Ali M, Sarfraz MS (2020) A fast and compact 3-D CNN for hyperspectral image classification. IEEE Geosci Remote Sens Lett"},{"issue":"12","key":"16159_CR2","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"16159_CR3","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.eswa.2018.11.042","volume":"120","author":"VS Bawa","year":"2019","unstructured":"Bawa VS, Kumar V (2019) Linearized sigmoidal activation: A novel activation function with tractable non-linear characteristics to boost representation capability. Expert Syst Appl 120:346\u2013356","journal-title":"Expert Syst Appl"},{"key":"16159_CR4","doi-asserted-by":"crossref","unstructured":"Bozkurt F (2022) Skin lesion classification on dermatoscopic images using effective data augmentation and pre-trained deep learning approach. Multimed Tools Appl\u00a082(12):18985\u201319003.\u00a0https:\/\/link.springer.com\/article\/10.1007\/s11042-022-14095-1","DOI":"10.1007\/s11042-022-14095-1"},{"issue":"2","key":"16159_CR5","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/0021-9045(92)90081-X","volume":"70","author":"CK Chui","year":"1992","unstructured":"Chui CK, Li X (1992) Approximation by ridge functions and neural networks with one hidden layer. J Approx Theory 70(2):131\u2013141","journal-title":"J Approx Theory"},{"key":"16159_CR6","doi-asserted-by":"crossref","unstructured":"Chung H, Lee SJ, Park JG (2016) Deep neural network using trainable activation functions. In 2016 International Joint Conference on Neural Networks (IJCNN) (pp 348-352). IEEE","DOI":"10.1109\/IJCNN.2016.7727219"},{"key":"16159_CR7","unstructured":"Clevert D-A, Unterthiner T, Hochreiter S (2016) Fast and accurate deep network learning by exponential linear units (ELUs). In Proceedings of the international conference on learning representations(ICLR 2016)"},{"issue":"10","key":"16159_CR8","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1016\/j.patcog.2005.03.024","volume":"38","author":"G Daqi","year":"2005","unstructured":"Daqi G, Yan J (2005) Classification methodologies of multilayer perceptrons with sigmoid activation functions. Pattern Recogn 38(10):1469\u20131482","journal-title":"Pattern Recogn"},{"key":"16159_CR9","doi-asserted-by":"publisher","first-page":"19495","DOI":"10.1007\/s11042-019-7330-0","volume":"78","author":"D Das","year":"2019","unstructured":"Das D, Nayak DR, Dash R, Majhi B (2019) An empirical evaluation of extreme learning machine: application to handwritten character recognition. Multimed Tools Appl 78:19495\u201319523","journal-title":"Multimed Tools Appl"},{"key":"16159_CR10","doi-asserted-by":"crossref","unstructured":"Ding B, Qian H, Zhou J (2018) Activation functions and their characteristics in deep neural networks. In 2018 Chinese control and decision conference (CCDC) (pp 1836\u20131841). IEEE.\u00a0https:\/\/ieeexplore.ieee.org\/abstract\/document\/8407425","DOI":"10.1109\/CCDC.2018.8407425"},{"key":"16159_CR11","doi-asserted-by":"crossref","unstructured":"Dubey AK, Jain V (2019) Comparative study of convolution neural network\u2019s relu and leaky-relu activation functions. In: In Applications of Computing, Automation and Wireless Systems in Electrical Engineering (pp 873\u2013880). Springer, Singapore","DOI":"10.1007\/978-981-13-6772-4_76"},{"key":"16159_CR12","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning (pp 1050\u20131059). PMLR.\u00a0https:\/\/proceedings.mlr.press\/v48\/gal16.html?trk=public_post_comment-text"},{"key":"16159_CR13","doi-asserted-by":"crossref","unstructured":"Hao S, Zhou Y, Guo Y (2020) A brief survey on semantic segmentation with deep learning. Neurocomputing 406:302\u2013321.\u00a0https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0925231220305476","DOI":"10.1016\/j.neucom.2019.11.118"},{"key":"16159_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"16159_CR15","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 770\u2013778).\u00a0https:\/\/openaccess.thecvf.com\/content_cvpr_2016\/html\/He_Deep_Residual_Learning_CVPR_2016_paper.html","DOI":"10.1109\/CVPR.2016.90"},{"key":"16159_CR16","unstructured":"Rohit (n.d.) GitHub - 1297rohit\/RCNN: step-by-step implementation of R-CNN from scratch in python. GitHub. https:\/\/github.com\/1297rohit\/RCNN. Accessed 5 Sep 2022"},{"key":"16159_CR17","unstructured":"Divamgupta (n.d.) GitHub - divamgupta\/image-segmentation-keras: implementation of Segnet, FCN, UNet , PSPNet and other models in Keras. GitHub. https:\/\/github.com\/divamgupta\/image-segmentation-keras. Accessed 18 Aug 2022"},{"key":"16159_CR18","unstructured":"Kulkarnikeerti (n.d.) GitHub - kulkarnikeerti\/segnet-semantic-segmentation: deep convolutional encoder-decoder network for image segmentation.\u00a0 GitHub. https:\/\/github.com\/kulkarnikeerti\/SegNet-Semantic-Segmentation. Accessed 18 Aug 2022"},{"key":"16159_CR19","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 4700\u20134708).\u00a0https:\/\/openaccess.thecvf.com\/content_cvpr_2017\/html\/Huang_Densely_Connected_Convolutional_CVPR_2017_paper.html","DOI":"10.1109\/CVPR.2017.243"},{"key":"16159_CR20","unstructured":"Kamruzzaman J (2002) Arctangent activation function to accelerate backpropagation learning. IEICE Trans Fundam Electron Commun Comput Sci 85(10):2373\u20132376.\u00a0https:\/\/search.ieice.org\/bin\/summary.php?id=e85-a_10_2373"},{"key":"16159_CR21","unstructured":"Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self-normalizing neural networks. Adv Neural Inf Proces Syst 30.\u00a0https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/5d44ee6f2c3f71b73125876103c8f6c4-Abstract.html"},{"key":"16159_CR22","doi-asserted-by":"crossref","unstructured":"Lau MM, Lim KH (2017) Investigation of activation functions in deep belief network. In 2017 2nd international conference on control and robotics engineering (ICCRE) (pp 201\u2013206). IEEE.\u00a0https:\/\/ieeexplore.ieee.org\/abstract\/document\/7935070","DOI":"10.1109\/ICCRE.2017.7935070"},{"key":"16159_CR23","doi-asserted-by":"crossref","unstructured":"Li S, Song W, Fang L, Chen Y, Ghamisi P, Benediktsson JA (2019) Deep learning for hyperspectral image classification: An overview. IEEE Trans Geosci Remote Sens 57(9):6690\u20136709.\u00a0https:\/\/ieeexplore.ieee.org\/abstract\/document\/8697135","DOI":"10.1109\/TGRS.2019.2907932"},{"key":"16159_CR24","doi-asserted-by":"crossref","unstructured":"Liew SS, Khalil-Hani M, Bakhteri R (2016) Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems. Neurocomputing 216:718\u2013734.\u00a0https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0925231216308797","DOI":"10.1016\/j.neucom.2016.08.037"},{"key":"16159_CR25","unstructured":"Lu L, Shin Y, Su Y, Karniadakis GE (2019) Dying relu and initialization: Theory and numerical examples. arXiv preprint arXiv:1903.06733.\u00a0https:\/\/arxiv.org\/abs\/1903.06733"},{"key":"16159_CR26","doi-asserted-by":"crossref","unstructured":"Lv W, Wang X (2020) Overview of hyperspectral image classification. J Sens 2020","DOI":"10.1155\/2020\/4817234"},{"key":"16159_CR27","unstructured":"Misra D (2019) Mish: A self regularized non-monotonic neural activation function arXiv preprint arXiv:1908.08681, 4(2), 10-48550"},{"key":"16159_CR28","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10) (pp 807\u2013814).\u00a0https:\/\/www.cs.toronto.edu\/~hinton\/absps\/reluICML.pdf"},{"issue":"2","key":"16159_CR29","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1109\/TNNLS.2020.2979670","volume":"32","author":"DW Otter","year":"2020","unstructured":"Otter DW, Medina JR, Kalita JK (2020) A survey of the usages of deep learning for natural language processing. IEEE Trans Neural Netw Learn Syst 32(2):604\u2013624","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"16159_CR30","unstructured":"Ramachandran P, Zoph B, Le QV (2017) Swish: a self-gated activation function arXiv preprint arXiv:1710.05941, 7(1), 5"},{"key":"16159_CR31","doi-asserted-by":"crossref","unstructured":"Shen SL, Zhang N, Zhou A, Yin ZY (2022) Enhancement of neural networks with an alternative activation function tanhLU. Expert Syst Appl 199:117181.\u00a0https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0957417422005681","DOI":"10.1016\/j.eswa.2022.117181"},{"key":"16159_CR32","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.\u00a0https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"16159_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 2818\u20132826)","DOI":"10.1109\/CVPR.2016.308"},{"key":"16159_CR34","unstructured":"Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp 6105\u20136114). PMLR"},{"key":"16159_CR35","doi-asserted-by":"crossref","unstructured":"Wang MX, Qu Y (2022) Approximation capabilities of neural networks on unbounded domains. Neural Netw 145:56\u201367.\u00a0https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0893608021003920","DOI":"10.1016\/j.neunet.2021.10.001"},{"key":"16159_CR36","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.neucom.2019.07.017","volume":"363","author":"X Wang","year":"2019","unstructured":"Wang X, Qin Y, Wang Y, Xiang S, Chen H (2019) ReLTanh: An activation function with vanishing gradient resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis. Neurocomputing 363:88\u201398","journal-title":"Neurocomputing"},{"key":"16159_CR37","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2020.01.085","volume":"396","author":"X Wu","year":"2020","unstructured":"Wu X, Sahoo D, Hoi SC (2020) Recent advances in deep learning for object detection. Neurocomputing 396:39\u201364","journal-title":"Neurocomputing"},{"key":"16159_CR38","unstructured":"Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853"},{"issue":"10","key":"16159_CR39","doi-asserted-by":"publisher","first-page":"7427","DOI":"10.1007\/s10489-021-02247-z","volume":"51","author":"Y Ying","year":"2021","unstructured":"Ying Y, Zhang N, Shan P, Miao L, Sun P, Peng S (2021) PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid. Appl Intell 51(10):7427\u20137439","journal-title":"Appl Intell"},{"issue":"1","key":"16159_CR40","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2010.939038","volume":"28","author":"D Yu","year":"2010","unstructured":"Yu D, Deng L (2010) Deep learning and its applications to signal and information processing [exploratory dsp]. IEEE Signal Process Mag 28(1):145\u2013154","journal-title":"IEEE Signal Process Mag"},{"key":"16159_CR41","doi-asserted-by":"publisher","first-page":"72727","DOI":"10.1109\/ACCESS.2020.2987829","volume":"8","author":"Y Yu","year":"2020","unstructured":"Yu Y, Adu K, Tashi N, Anokye P, Wang X, Ayidzoe MA (2020) Rmaf: Relu-memristor-like activation function for deep learning. IEEE Access 8:72727\u201372741","journal-title":"IEEE Access"},{"key":"16159_CR42","doi-asserted-by":"crossref","unstructured":"Zaheer R, Shaziya H (2018) GPU-based empirical evaluation of activation functions in convolutional neural networks. In 2018 2nd International Conference on Inventive Systems and Control (ICISC) (pp 769-773). IEEE","DOI":"10.1109\/ICISC.2018.8398903"},{"key":"16159_CR43","doi-asserted-by":"crossref","unstructured":"Zhang Z, Geiger J, Pohjalainen J, Mousa AED, Jin W, Schuller B (2018) Deep learning for environmentally robust speech recognition: An overview of recent developments. ACM Trans Intell Syst Technol (TIST) 9(5):1\u201328.\u00a0https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3178115","DOI":"10.1145\/3178115"},{"key":"16159_CR44","doi-asserted-by":"crossref","unstructured":"Zhang Q, Liu Y, Gong C, Chen Y, Yu H (2020) Applications of deep learning for dense scenes analysis in agriculture: a review.\u00a0Sensors\u00a020(5):1520.\u00a0https:\/\/www.mdpi.com\/1424-8220\/20\/5\/1520","DOI":"10.3390\/s20051520"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16159-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16159-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16159-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T19:44:00Z","timestamp":1729799040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16159-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":44,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["16159"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16159-2","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,7,21]]},"assertion":[{"value":"13 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}