{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T09:46:41Z","timestamp":1782640001660,"version":"3.54.5"},"reference-count":140,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,7,6]],"date-time":"2019-07-06T00:00:00Z","timestamp":1562371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,7,6]],"date-time":"2019-07-06T00:00:00Z","timestamp":1562371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s40537-019-0197-0","type":"journal-article","created":{"date-parts":[[2019,7,6]],"date-time":"2019-07-06T03:02:57Z","timestamp":1562382177000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10816,"title":["A survey on Image Data Augmentation for Deep Learning"],"prefix":"10.1186","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6253-6861","authenticated-orcid":false,"given":"Connor","family":"Shorten","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,7,6]]},"reference":[{"key":"197_CR1","first-page":"1106","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1106\u201314.","journal-title":"Adv Neural Inf Process Syst"},{"key":"197_CR2","unstructured":"Karen S, Andrew Z. Very deep convolutional networks for large-scale image recognition. arXiv e-prints. 2014."},{"key":"197_CR3","unstructured":"Kaiming H, Xiangyu Z, Shaoqing R, Jian S. Deep residual learning for image recognition. In: CVPR, 2016."},{"key":"197_CR4","unstructured":"Christian S, Vincent V, Sergey I, Jon S, Zbigniew W. Rethinking the inception architecture for computer vision. arXiv e-prints, 2015."},{"key":"197_CR5","unstructured":"Gao H, Zhuang L, Laurens M, Kilian QW. Densely connected convolutional networks. arXiv preprint. 2016."},{"key":"197_CR6","unstructured":"Jan K, Vladimir G, Daniel C. Regularization for deep learning: a taxonomy. arXiv preprint. 2017."},{"issue":"1","key":"197_CR7","first-page":"1929","volume":"15","author":"S Nitish","year":"2014","unstructured":"Nitish S, Geoffrey H, Alex K, Ilya S, Ruslan S. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929\u201358.","journal-title":"J Mach Learn Res."},{"key":"197_CR8","unstructured":"Jonathan T, Ross G, Arjun J, Yann L, Christoph B. Efficient object localization using convolutional networks. In: CVPR\u201915. 2015."},{"key":"197_CR9","unstructured":"Sergey I, Christan S. Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML; 2015."},{"key":"197_CR10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"W Karl","year":"2016","unstructured":"Karl W, Taghi MK, DingDing W. A survey of transfer learning. J Big Data. 2016;3:9.","journal-title":"J Big Data."},{"issue":"5","key":"197_CR11","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1109\/TNNLS.2014.2330900","volume":"26","author":"L Shao","year":"2015","unstructured":"Shao L. Transfer learning for visual categorization: a survey. IEEE Trans Neural Netw Learn Syst. 2015;26(5):1019\u201334.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"197_CR12","unstructured":"Jia D, Wei D, Richard S, Li-Jia L, Kai L, Li F-F. ImageNet: a large-scale hierarchical image database. In: CVPR09, 2009."},{"key":"197_CR13","doi-asserted-by":"crossref","unstructured":"Amir Z, Alexander S, William S, Leonidas G, Jitendra M, Silvio S. Taskonomy: disentangling task transfer learning. In: CVPR \u201818. 2018.","DOI":"10.1109\/CVPR.2018.00391"},{"key":"197_CR14","first-page":"3320","volume":"27","author":"J Yosinski","year":"2014","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H. How transferable are features in deep neural networks? Adv Neural Inf Process Syst. 2014;27:3320\u20138.","journal-title":"Adv Neural Inf Process Syst"},{"key":"197_CR15","first-page":"625","volume":"11","author":"D Erhan","year":"2010","unstructured":"Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P. Why does unsupervised pre-training help deep learning? J Mach Learn Res. 2010;11:625\u201360.","journal-title":"J Mach Learn Res"},{"key":"197_CR16","unstructured":"Mark P, Dean P, Geoffrey H, Tom MM. Zero-shot learning with semantic output codes. In: NIPS; 2009."},{"key":"197_CR17","unstructured":"Yongqin X, Christoph HL, Bernt S, Zeynep A. Zero-shot learning\u2014a comprehensive evaluation of the good, the bad and the ugly. arXiv preprint. 2018."},{"key":"197_CR18","unstructured":"Yaniv T, Ming Y, Marc\u2019 AR, Lior W. DeepFace: closing the gap to human-level performance in face verification. In: CVPR \u201914; 2014."},{"key":"197_CR19","unstructured":"Gregory K, Richard Z, Ruslan S. Siamese neural networks for one-shot image recognition. In: ICML Deep Learning workshop; 2015."},{"key":"197_CR20","unstructured":"Adam S, Sergey B, Matthew B, Dean W, Timothy L. One-shot learning with memory-augmented neural networks. arXiv preprint. 2016."},{"key":"197_CR21","unstructured":"Tomas M, Ilya S, Kai C, Greg C, Jeffrey D. Distributed representations of words and phrases and their compositionality. Accepted to NIPS 2013."},{"key":"197_CR22","unstructured":"Jeffrey P, Richard S, Christopher DM. GloVe: global vectors for word representation. In: Proceedings of the empirical methods in natural language processing (EMNLP 2014) 12. 2014."},{"key":"197_CR23","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MIS.2009.36","volume":"24","author":"A Halevy","year":"2009","unstructured":"Halevy A, Norvig P, Pereira F. The unreasonable effectiveness of data. IEEE Intell Syst. 2009;24:8\u201312.","journal-title":"IEEE Intell Syst"},{"key":"197_CR24","unstructured":"Chen S, Abhinav S, Saurabh S, Abhinav G. Revisting unreasonable effectivness of data in deep learning era. In: ICCV; 2017. p. 843\u201352."},{"key":"197_CR25","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115\u20138.","journal-title":"Nature"},{"key":"197_CR26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"L Geert","year":"2017","unstructured":"Geert L, Thijs K, Babak EB, Arnaud AAS, Francesco C, Mohsen G, Jeroen AWM, van Bram G, Clara IS. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60\u201388.","journal-title":"Med Image Anal."},{"key":"197_CR27","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s40537-018-0151-6","volume":"5","author":"LL Joffrey","year":"2018","unstructured":"Joffrey LL, Taghi MK, Richard AB, Naeem S. A survey on addressing high-class imbalance in big data. Springer J Big Data. 2018;5:42.","journal-title":"Springer J Big Data."},{"issue":"11","key":"197_CR28","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278\u2013324.","journal-title":"Proc IEEE"},{"key":"197_CR29","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"VC Nitesh","year":"2002","unstructured":"Nitesh VC, Kevin WB, Lawrence OH, Kegelmeyer W. SMOTE: synthetic minority over-sampling technique. J Artif Intellig Res. 2002;16:321\u201357.","journal-title":"J Artif Intellig Res."},{"key":"197_CR30","unstructured":"Hui H, Wen-Yuan W, Bing-Huan M. Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: Proceedings of ICIC, vol. 3644, Lecture Notes in Computer Science, New York. 2005, p. 878\u201387."},{"key":"197_CR31","unstructured":"Ian JG, Jean PA, Mehdi M, Bing X, David WF, Sherjil O, Aaron C, Yoshua B. Generative adversarial nets. NIPS. 2014."},{"key":"197_CR32","unstructured":"Leon AG, Alexander SE, Matthias B. A neural algorithm of artistic style. ArXiv. 2015."},{"key":"197_CR33","unstructured":"Barret Z, Quoc VL. Neural architecture search with reinforcement learning. In: International conference on learning representatoins, 2017."},{"key":"197_CR34","unstructured":"Tero K, Timo A, Samuli L, Jaakko L. Progressive growing of GANs for improved quality, stability, and variation. CoRR, abs\/1710.10196, 2017."},{"key":"197_CR35","first-page":"694","volume":"2016","author":"J Justin","year":"2016","unstructured":"Justin J, Alexandre A, Li FF. Perceptual losses for real-time style transfer and super-resolution. ECCV. 2016;2016:694\u2013711.","journal-title":"ECCV."},{"key":"197_CR36","unstructured":"Luis P, Jason W. The effectiveness of data augmentation in image classification using deep learning. In: Stanford University research report, 2017."},{"key":"197_CR37","doi-asserted-by":"crossref","unstructured":"Lemley J, Barzrafkan S, Corcoran P. Smart augmentation learning an optimal data augmentation strategy. In: IEEE Access. 2017.","DOI":"10.1109\/ACCESS.2017.2696121"},{"key":"197_CR38","unstructured":"Ekin DC, Barret Z, Dandelion M, Vijay V, Quoc VL. AutoAugment: learning augmentation policies from data. ArXiv preprint. 2018."},{"key":"197_CR39","unstructured":"Xin Y, Paul SB, Ekta W. Generative adversarial network in medical imaging: a review. arXiv preprint. 2018."},{"key":"197_CR40","unstructured":"Jelmer MW, Tim L, Max AV, Ivana I. Generative adversarial networks for noise reduction in low-dose CT. In: IEEE Transactions on Medical Imaging. 2017."},{"key":"197_CR41","unstructured":"Ohad S, Tammy RR. Accelerated magnetic resonance imaging by adversarial neural network. In: DLMIA\/ML-CDS@MICCAI, 2017."},{"key":"197_CR42","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1016\/j.neuroimage.2018.03.045","volume":"174","author":"Y Wang","year":"2018","unstructured":"Wang Y, Biting Y, Wang L, Chen Z, Lalush DS, Lin W, Xi W, Zhou J, Shen D, Zhou L. 3D conditional generative adversarial networks for high-quality PET image estimation at low dose. NeuroImage. 2018;174:550\u201362.","journal-title":"NeuroImage"},{"key":"197_CR43","unstructured":"Dwarikanath M, Behzad B. Retinal vasculature segmentation using local saliency maps and generative adversarial networks for image super resolution. arXiv preprint. 2017."},{"key":"197_CR44","doi-asserted-by":"crossref","unstructured":"Francesco C, Aldo M, Claudio S, Giorgio T. Biomedical data augmentation using generative adversarial neural networks. In: International conference on artificial neural networks. Berlin: Springer; 2017. P. 626\u201334.","DOI":"10.1007\/978-3-319-68612-7_71"},{"key":"197_CR45","first-page":"105741","volume":"10574","author":"B Camilo","year":"2018","unstructured":"Camilo B, Andrew JP, Larry TD, Allen TN, Susan MR, Bennett AL. Learning implicit brain MRI manifolds with deep learning. Int Soc Opt Photonics. 2018;10574:105741.","journal-title":"Int Soc Opt Photonics."},{"key":"197_CR46","unstructured":"Maria JMC, Sarfaraz H, Jeremy B, Ulas B. How to fool radiologists with generative adversarial networks? A visual turing test for lung cancer diagnosis. arXiv preprint. 2017."},{"key":"197_CR47","unstructured":"Baur C, Albarqouni S, Navab N. MelanoGANs: high resolution skin lesion synthesis with GANs. arXiv preprint. 2018."},{"key":"197_CR48","unstructured":"Madani A, Moradi M, Karargyris A, Syeda-Mahmood T. Chest x-ray generation and data augmentation for cardiovascular abnormality classification. In: Medical imaging 2018. Image Processing 2018;10574:105741."},{"key":"197_CR49","unstructured":"Maayan F-A, Eyal K, Jacob G, Hayit G. GAN-based data augmentation for improved liver lesion classification. arXiv preprint. 2018."},{"key":"197_CR50","unstructured":"Joseph R, Santosh D, Ross G, Ali F. You only look once: unified, real-time object detection. In: CVPR\u201816. 2016."},{"key":"197_CR51","unstructured":"Ross G, Jeff D, Trevor D, Jitendra M. Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR \u201814. 2014."},{"key":"197_CR52","unstructured":"Ross G. Fast R-CNN. CoRR, abs\/1504.08083. 2015."},{"key":"197_CR53","unstructured":"Shaoqing R, Kaiming H, Ross G, Jian S. Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, 2015."},{"key":"197_CR54","unstructured":"Jonathan L, Evan S, Trevor D. Fully convolutional networks for semantic segmentation. CoRR, abs\/1411.4038. 2014."},{"key":"197_CR55","doi-asserted-by":"crossref","unstructured":"Olaf R, Philipp F, Thomas B. U-Net: convolutional networks for biomedical image segmentation. In: MICCAI. Springer; 2015, p. 234\u201341.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"197_CR56","unstructured":"Hessam B, Maxwell H, Mohammad R, Ali F. Label refinery: improving imagenet classification through label progression. arXiv preprint. 2018."},{"key":"197_CR57","unstructured":"Francisco JM-B, Fiammetta S, Jose MJ, Daniel U, Leonardo F. Forward noise adjustment scheme for data augmentation. arXiv preprints. 2018."},{"key":"197_CR58","unstructured":"Dua D, Karra TE. UCI machine learning repository [ http:\/\/archive.ics.uci.edu\/ml ]. Irvine, CA: University of California, School of Information and Computer Science; 2017."},{"key":"197_CR59","unstructured":"Ken C, Karen S, Andrea V, Andrew Z. Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of BMVC. 2014."},{"key":"197_CR60","unstructured":"Mark E, Luc VG, Christopher KIW, John W, Andrew Z. The pascal visual object classes (VOC) challenge. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2008\/workshop\/ . 2008."},{"key":"197_CR61","unstructured":"Aranzazu J, Miguel P, Mikel G, Carlos L-M, Daniel P. A comparison study of different color spaces in clustering based image segmentation. IPMU; 2010."},{"key":"197_CR62","unstructured":"Quanzeng Y, Jiebo L, Hailin J, Jianchao Y. Robust image sentiment analysis using progressively trained and domain transferred deep networks. In: AAAI. 2015, p. 381\u20138."},{"key":"197_CR63","unstructured":"Luke T, Geoff N. Improving deep learning using generic data augmentation. arXiv preprint. 2017."},{"key":"197_CR64","unstructured":"Guoliang K, Xuanyi D, Liang Z, Yi Y. PatchShuffle regularization. arXiv preprint. 2017."},{"key":"197_CR65","unstructured":"Hiroshi I. Data augmentation by pairing samples for images classification. ArXiv e-prints. 2018."},{"key":"197_CR66","unstructured":"Cecilia S, Michael JD. Improved mixed-example data augmentation. ArXiv preprint. 2018."},{"key":"197_CR67","unstructured":"Daojun L, Feng Y, Tian Z, Peter Y. Understanding mixup training methods. In: IEEE access. 2018. p. 1."},{"key":"197_CR68","unstructured":"Ryo T, Takashi M. Data augmentation using random image cropping and patches for deep CNNs. arXiv preprints. 2018."},{"key":"197_CR69","unstructured":"Yoshua B, Jerome L, Ronan C, Jason W. Curriculum learning. In: Proceedings of the 26th annual international conference on machine learning, ACM. 2009, p. 41\u20138."},{"key":"197_CR70","unstructured":"Zhun Z, Liang Z, Guoliang K, Shaozi L, Yi Y. Random erasing data augmentation. ArXiv e-prints. 2017."},{"key":"197_CR71","unstructured":"Terrance V, Graham WT. Improved regularization of convolutional neural networks with cutout. arXiv preprint. 2017."},{"key":"197_CR72","unstructured":"Agnieszka M, Michal G. Data augmentation for improving deep learning in image classification problem. In: IEEE 2018 international interdisciplinary Ph.D. Workshop, 2018."},{"key":"197_CR73","unstructured":"Jonathan K, Michael S, Jia D, Li F-F. 3D object representations for fine-grained categorization. In: 4th IEEE Workshop on 3D Representation and Recognition, at ICCV 2013 (3dRR-13). Sydney, Australia. Dec. 8, 2013."},{"key":"197_CR74","unstructured":"Tomohiko K, Michiaki I. Icing on the cake: an easy and quick post-learning method you can try after deep learning. arXiv preprints. 2018."},{"key":"197_CR75","unstructured":"Terrance V, Graham WT. Dataset augmentation in feature space. In: Proceedings of the international conference on machine learning (ICML), workshop track, 2017."},{"key":"197_CR76","unstructured":"Sebastien CW, Adam G, Victor S, Mark DM. Understanding data augmentation for classification: when to warp? CoRR, abs\/1609.08764, 2016."},{"key":"197_CR77","unstructured":"Seyed-Mohsen MD, Alhussein F, Pascal F. DeepFool: a simple and accurate method to fool deep neural networks. arXiv preprint. 2016."},{"key":"197_CR78","unstructured":"Jiawei S, Danilo VV, Sakurai K. One pixel attack for fooling deep neural networoks. arXiv preprints. 2018."},{"key":"197_CR79","unstructured":"Michal Z, Konrad Z, Negar R, Pedro OP. Adversarial framing for image and video classification. arXiv preprints. 2018."},{"key":"197_CR80","unstructured":"Logan E, Brandon T, Dimitris T, Ludwig S, Aleksander M. A rotation and a translation suffice: fooling CNNs with simple transformations. ArXiv preprint. 2018."},{"key":"197_CR81","unstructured":"Goodfellow I, Shlens J, Szegedy C. Explaining and Harnessing Adversarial Examples. International Conference on Learning Representations, 2015."},{"key":"197_CR82","unstructured":"Ian JG, David W-F, Mehdi M, Aaron C, Yoshua B. Maxout networks. arXiv preprint. 2013."},{"key":"197_CR83","unstructured":"Shuangtao L, Yuanke C, Yanlin P, Lin B. Learning more robust features with adversarial training. ArXiv preprints. 2018."},{"key":"197_CR84","unstructured":"Lingxi X, Jingdong W, Zhen W, Meng W, Qi T. DisturbLabel: regularizing CNN on the loss layer. arXiv preprint. 2016."},{"key":"197_CR85","unstructured":"Christopher B, Liang C, Ricardo GPB, Roger G, Alexander H, David AD, Maria VH, Joanna W, Daniel R. GAN augmentation: augmenting training data using generative adversarial networks. arXiv preprint. 2018."},{"key":"197_CR86","unstructured":"Doersch C. Tutorial on Variational Autoencoders. ArXiv e-prints. 2016."},{"key":"197_CR87","first-page":"2431","volume":"9","author":"M Laurens","year":"2008","unstructured":"Laurens M, Geoffrey H. Visualizing data using t-SNE. J Mach Learn Res. 2008;9:2431\u201356.","journal-title":"J Mach Learn Res."},{"key":"197_CR88","unstructured":"Jeff D, Philipp K, Trevor D. Adversarial feature learning. In: CVPR\u201916. 2016."},{"key":"197_CR89","unstructured":"Lin Z, Shi Y, Xue Z. IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection. arXiv preprint; 2018."},{"key":"197_CR90","unstructured":"William F, Mihaela R, Balaji L, Andrew MD, Shakir M, Ian G. Many paths to equilibrium: GANs do not need to decrease a divergence at every step. In: International conference on learning representations (ICLR); 2017."},{"key":"197_CR91","unstructured":"Alec R, Luke M, Soumith C. Unsupervised representation learning with deep convolutional generative adversarial networks. ICLR, 2016."},{"key":"197_CR92","unstructured":"Jun-Yan Z, Taesung P, Phillip I, Alexei AE. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: International conference on cmoputer vision (ICCV), 2017."},{"key":"197_CR93","unstructured":"Xinyue Z, Yifan L, Zengchang Q, Jiahong L. Emotion classification with data augmentation using generative adversarial networks. CoRR, vol. abs\/1711.00648. 2017."},{"key":"197_CR94","doi-asserted-by":"crossref","unstructured":"Goodfellow IJ, Erhan D, Carrier PL, Courville A, Mirza M, Hamner B, Cukierski W, Tang Y, Thaler D, Lee DH, et al. Challenges in representation learning: A report on three machine learning contests. In: NIPS. Berlin: Springer; 2013. p.117\u201324.","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"197_CR95","unstructured":"Mehdi M, Simon O. Conditional generative adversarial nets. arXiv preprint. 2014."},{"key":"197_CR96","unstructured":"Mario L, Karol K, Marcin M, Olivier B, Sylvain G. Are GANs created equal? A large-scale study. arXiv preprint. 2018."},{"key":"197_CR97","unstructured":"Swee KL, Yi L, Ngoc-Trung T, Ngai-Man C, Gemma R, Yuval E. DOPING: generative data augmentation for unsupervised anomaly detection with GAN. arXiv preprint. 2018."},{"key":"197_CR98","unstructured":"Alireza M, Jonathon S, Navdeep J, Ian G, Brendan F. Adversarial autoencoders. arXiv preprint. 2015."},{"key":"197_CR99","unstructured":"Tim S, Ian G, Wojciech Z, Vicki C, Alec R, Xi C. Improved techniques for training GANs. arXiv preprint. 2016."},{"key":"197_CR100","unstructured":"Yanghao L, Naiyan W, Jiaying L, Xiaodi H. Demistifying neural style transfer. arXiv preprint. 2017."},{"key":"197_CR101","unstructured":"Khizar H. Super-resolution via deep learning. arXiv preprint. 2017."},{"key":"197_CR102","unstructured":"Dmitry U, Andrea V, Victor L. Instance normalization: the missing ingredient for fast stylization. arXiv preprint. 2016."},{"key":"197_CR103","unstructured":"Philip TJ, Amir AA, Stephen B, Toby B, Boguslaw O. Style augmentation: data augmentation via style randomization. arXiv e-prints. 2018."},{"key":"197_CR104","unstructured":"Josh T, Rachel F, Alex R, Jonas S, Wojciech Z, Pieter A. Domain randomization for transferring deep neural networks from simulation to the real world. arXiv preprint. 2017."},{"key":"197_CR105","unstructured":"Ashish S, Tomas P, Oncel T, Josh S, Wenda W, Russ W. Learning from simulated and unsupervised images through adversarial training. In: Conference on computer vision and pattern recognition, 2017."},{"key":"197_CR106","unstructured":"Stephan RR, Vibhav V, Stefan R, Vladlen K. Playing for data: ground truth from computer games. In: European conference on computer vision (ECCV); 2016."},{"issue":"2","key":"197_CR107","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"Gabriel J Brostow","year":"2008","unstructured":"Brostow Gabriel J, Fauqueur Julien, Cipolla Roberto. Semantic object classes in video: a high-definition ground truth database. Pattern Recogn Lett. 2008;30(2):88\u201397.","journal-title":"Pattern Recogn Lett"},{"key":"197_CR108","unstructured":"Marius C, Mohamed O, Sebastian R, Timo R, Markus E, Rodrigo B, Uwe F, Stefan R, Bernt S. The cityscape dataset for semantic urban scene understanding. In: CVPR; 2016."},{"key":"197_CR109","unstructured":"Esteban R, Sherry M, Andrew S, Saurabh S, Yutaka LS, Jie T, Quoc VL, Alexey K. Large-scale evolution of image classifiers. In: Proceedings of the 34th international conference on machine learning (ICML \u201817). 2017."},{"key":"197_CR110","unstructured":"Esteban R, Alok A, Yanping H, Quoc VL. Regularized evolution for image classifier architecture search. arXiv preprint. 2018."},{"key":"197_CR111","unstructured":"Tim S, Jonathan H, Xi C, Szymon S, Ilya S. Evolution strategies as a scalable alternative to reinforcement learning. arXiv e-prints. 2017."},{"key":"197_CR112","unstructured":"Horia M, Aurelia G, Benjamin R. Simple random search provides a competitive approach to reinforcement learning. In: Advances in neural information processing systems (NIPS); 2018."},{"key":"197_CR113","first-page":"91","volume":"2004","author":"GL David","year":"2004","unstructured":"David GL. Distinctive image features from scale-invariant keypoints. Int J Comput Vis. 2004;2004:91\u2013110.","journal-title":"Int J Comput Vis."},{"key":"197_CR114","unstructured":"Navneet D, Bill T. Histograms of oriented gradients for human detection. In: CVPR, 2005."},{"key":"197_CR115","volume-title":"Learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Reinforcement AG. Learning: an introduction. New York: MIT Press; 1998."},{"key":"197_CR116","unstructured":"Mingyang G, Kele X, Bo D, Huaimin W, Lei Z. Learning data augmentation policies using augmented random search. arXiv preprint. 2018."},{"key":"197_CR117","unstructured":"Tran NM, Mathieu S, Hoang TL, Martin W. Automated image data preprocessing with deep reinforcement learning. arXiv preprints. 2018."},{"issue":"02","key":"197_CR118","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1142\/S0218488598000094","volume":"6","author":"S Hochreiter","year":"1998","unstructured":"Hochreiter S. The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncertain Fuzzin Know Based Syst. 1998;6(02):107\u201316.","journal-title":"Int J Uncertain Fuzzin Know Based Syst"},{"key":"197_CR119","unstructured":"Jia S, Wang P, Jia P, Hu S. Research on data augmentation for image classification based on convolutional neural networks. In: 2017 Chinese automation congress (CAC), 2017. p. 4165\u201370."},{"key":"197_CR120","unstructured":"Ilija R, Piotr D, Ross G, Georgia G, Kaiming H. Data distillation: towards omni-supervised learning. In: CVPR \u201918; 2018."},{"key":"197_CR121","unstructured":"Guotai W, Michael A, Sebastien O, Wenqi L, Jan D, Tom V. Test-time augmentation with uncertainty estimation for deep learning-based medical image segmentation. OpenReview.net. 2018."},{"key":"197_CR122","unstructured":"Fabio P, Christina V, Sandra A, Eduardo V. Data augmentation for skin lesion analysis. In: ISIC skin image analysis workshop and challenge @ MICCAI 2018. 2018."},{"key":"197_CR123","unstructured":"Karzuhisa M, Akira H, Akane M, Hiroshi K. Image classification of melanoma, nevus and seborrheic keratosis by deep neural network ensemble. In: International skin imaging collaboration (ISIC) 2017 challenge at the international symposium on biomedical imaging (ISBI). 2017."},{"key":"197_CR124","unstructured":"Max J, Karen S, Andrea V, Andrew Z. Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint. 2014."},{"key":"197_CR125","unstructured":"Florian S, Dmitry K, James P. FaceNet: a unified embedding for face recognition and clustering. In: CVPR \u201815. 2015."},{"key":"197_CR126","unstructured":"Xudong M, Qing L, Haoran X, Raymond YKL, Zhen W, Stephen PS. Least squares generative adversarial networks. In: International conference on computer vision (ICCV), 2017."},{"key":"197_CR127","unstructured":"Ren W, Shengen Y, Yi S, Qingqing D, Gang S. Deep image: scaling up image recognition. CoRR, abs\/1501.02876, 2015."},{"key":"197_CR128","doi-asserted-by":"crossref","unstructured":"Chao D, Chen CL, Kaiming H, Ziaoou T. Learning a deep convolutional network for image super-resolution. In: ECCV. Berlin: Springer; 2014. , p. 184\u201399.","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"197_CR129","unstructured":"Christian L, Lucas T, Ferenc H, Jose C, Andrew C, Alejandro A, Andrew A, Alykhan T, Johannes T, Zehan W, Wenzhe S. Photo-realistic single image super-resolution using a generative adversarial network. arXiv preprint. 2016."},{"key":"197_CR130","unstructured":"Han Z, Tao X, Hongsheng L, Shaoting Z, Xiaogang W, Xiaolei H, Dimitris M. StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV, 2017."},{"key":"197_CR131","unstructured":"Trishul C, Yutaka S, Johnson A, Karthik K. Project adam: building an efficient and scalable deep learning training system. In: Proceedings of OSDI. 2014. P. 571\u201382."},{"key":"197_CR132","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","volume":"106","author":"Mateusz Buda","year":"2018","unstructured":"Buda Mateusz, Maki Atsuto, Mazurowski Maciej A. A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks. 2018;106:249\u201359.","journal-title":"Neural Networks"},{"issue":"5","key":"197_CR133","first-page":"1097","volume":"39","author":"DJ Drown","year":"2009","unstructured":"Drown DJ, Khoshgoftaar TM, Seliya N. Evolutionary sampling and software quality modeling of high-assurance systems. IEEE Trans Syst. 2009;39(5):1097\u2013107.","journal-title":"IEEE Trans Syst."},{"key":"197_CR134","unstructured":"Jason Y, Jeff C, Anh N, Thomas F, Hod L. Understanding neural networks through deep visualization. In: European conference on computer vision (ECCV). Berlin: Springer; 2015. p. 818\u201333."},{"key":"197_CR135","unstructured":"Xiaofeng Z, Zhangyang W, Dong L, Qing L. DADA: deep adversarial data augmentation for extremely low data regime classification. arXiv preprint. 2018."},{"key":"197_CR136","unstructured":"Martin A, Paul B, Jianmin C, Zhifeng C, Andy D, Jeffrey D, Matthieu D, Sanjay G, Geoffrey I, Michael I, Manjunath K, Josh L, Rajat M, Sherry M, Derek GM, Benoit S, Paul T, Vijay V, Pete W, Matrin W, Yuan Y, Xiaoqiang Z. TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX symposium on operating system design and implementation (OSDI \u201816), 2016."},{"key":"197_CR137","unstructured":"Keras https:\/\/keras.io\/ . 2015."},{"key":"197_CR138","unstructured":"Alexander B, Alex P, Eugene K, Vladimir II, Alexandr AK. Albumentations: fast and flexible image augmentations. ArXiv preprints. 2018."},{"key":"197_CR139","unstructured":"Maayan F-A, Idit D, Eyal K, Michal A, Jacob G, Hayit G. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. arXiv preprint. 2018."},{"key":"197_CR140","doi-asserted-by":"crossref","unstructured":"Changhee H, Hideaki H, Leonardo R, Ryosuke A, Wataru S, Shinichi M, Yujiro F, Giancarlo M, Hideki N. GAN-based synthetic brain mr image generation. In: 2018 IEEE 15th International Symposium on biomedical imaging (ISBI 2018). IEEE, 2011. P. 734\u20138.","DOI":"10.1109\/ISBI.2018.8363678"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0197-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-019-0197-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0197-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T21:57:41Z","timestamp":1663883861000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-019-0197-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,6]]},"references-count":140,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["197"],"URL":"https:\/\/doi.org\/10.1186\/s40537-019-0197-0","relation":{"is-referenced-by":[{"id-type":"doi","id":"10.1038\/s41598-025-14786-3","asserted-by":"object"},{"id-type":"doi","id":"10.1007\/s13580-025-00743-6","asserted-by":"object"}]},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,6]]},"assertion":[{"value":"9 January 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"60"}}