{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T20:59:37Z","timestamp":1754600377075,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T00:00:00Z","timestamp":1673049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T00:00:00Z","timestamp":1673049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-022-01549-4","type":"journal-article","created":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T12:05:35Z","timestamp":1673093135000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards an Analytical Definition of Sufficient Data"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9124-5008","authenticated-orcid":false,"given":"Adam","family":"Byerly","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatiana","family":"Kalganova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,7]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li L-J, Kai Li, Fei-Fei L. ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on computer vision and pattern recognition, IEEE. 2010; p. 248\u201355. https:\/\/doi.org\/10.1109\/cvpr.2009.5206848.","key":"1549_CR1","DOI":"10.1109\/cvpr.2009.5206848"},{"doi-asserted-by":"crossref","unstructured":"Zhai X, Kolesnikov A, Houlsby N, Beyer L. Scaling vision transformers. 2021. arXiv:2106.04560.","key":"1549_CR2","DOI":"10.1109\/CVPR52688.2022.01179"},{"doi-asserted-by":"crossref","unstructured":"Byerly A, Kalganova T, Grichnik AJ. On the importance of capturing a sufficient diversity of perspective for the classification of micro-pcbs. In: intelligent decision technologies, Springer: Singapore; 2021. vol. 238, pp. 209\u201319.","key":"1549_CR3","DOI":"10.1007\/978-981-16-2765-1_17"},{"key":"1549_CR4","doi-asserted-by":"publisher","first-page":"48519","DOI":"10.1109\/ACCESS.2021.3066842","volume":"9","author":"A Byerly","year":"2021","unstructured":"Byerly A, Kalganova T. Homogeneous vector capsules enable adaptive gradient descent in convolutional neural networks. IEEE Access. 2021;9:48519\u201330. https:\/\/doi.org\/10.1109\/ACCESS.2021.3066842.","journal-title":"IEEE Access"},{"key":"1549_CR5","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton G. Visualizing data using t-SNE Laurens. J Mach Learn Res. 2008;9:2579\u2013605.","journal-title":"J Mach Learn Res"},{"doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J. UMAP: Uniform manifold approximation and projection for dimension reduction. 2018. arXiv:1802.03426.","key":"1549_CR6","DOI":"10.21105\/joss.00861"},{"issue":"1","key":"1549_CR7","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover T, Hart P. Nearest neighbor pattern classification. IEEE Trans Inf Theory. 1967;13(1):21\u20137. https:\/\/doi.org\/10.1109\/TIT.1967.1053964.","journal-title":"IEEE Trans Inf Theory"},{"issue":"3","key":"1549_CR8","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/TIT.1968.1054155","volume":"14","author":"P Hart","year":"1968","unstructured":"Hart P. The condensed nearest neighbor rule (corresp.). IEEE Trans Inf Theory. 1968;14(3):515\u20136. https:\/\/doi.org\/10.1109\/TIT.1968.1054155.","journal-title":"IEEE Trans Inf Theory"},{"issue":"6","key":"1549_CR9","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1109\/TIT.1975.1055464","volume":"21","author":"G Ritter","year":"1975","unstructured":"Ritter G, Woodruff H, Lowry S, Isenhour T. An algorithm for a selective nearest neighbor decision rule (corresp.). IEEE Trans Inf Theory. 1975;21(6):665\u20139. https:\/\/doi.org\/10.1109\/TIT.1975.1055464.","journal-title":"IEEE Trans Inf Theory"},{"issue":"3","key":"1549_CR10","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/TSMC.1972.4309137","volume":"SMC\u20132","author":"DL Wilson","year":"1972","unstructured":"Wilson DL. Asymptotic properties of nearest neighbor rules using edited data. IEEE Trans Syst Man Cybern. 1972;SMC\u20132(3):408\u201321. https:\/\/doi.org\/10.1109\/TSMC.1972.4309137.","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"1549_CR11","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1023\/A:1007626913721","volume":"38","author":"DR Wilson","year":"2000","unstructured":"Wilson DR, Martinez TR. Reduction techniques for instance-based learning algorithms. Mach Learn. 2000;38:257\u201386.","journal-title":"Mach Learn"},{"unstructured":"Albalate MTL. Data reduction techniques in classification processes. PhD thesis. 2007.","key":"1549_CR12"},{"doi-asserted-by":"crossref","unstructured":"V\u00e1zquez F, S\u00e1nchez JS, Pla F. A Stochastic approach to wilson\u2019s editing algorithm. In: Marques JS, P\u00e9rez de la Blanca N, Pina, P, editors. Pattern recognition and image analysis. Lecture Notes in Computer Science, vol 3523. Springer: Berlin, Heidelberg; 2005. pp. 35\u201342.","key":"1549_CR13","DOI":"10.1007\/11492542_5"},{"doi-asserted-by":"publisher","unstructured":"Chou C-H, Kuo B-H, Chang F. The generalized condensed nearest neighbor rule as a data reduction method. In: 18th International Conference on pattern recognition (ICPR\u201906). 2006; vol. 2, p. 556\u20139. https:\/\/doi.org\/10.1109\/ICPR.2006.1119.","key":"1549_CR14","DOI":"10.1109\/ICPR.2006.1119"},{"doi-asserted-by":"publisher","unstructured":"Ougiaroglou S, Evangelidis G. Efficient dataset size reduction by finding homogeneous clusters. In: Balkan Conference in Informatics (BCI). 2012; p. 168\u2013173. https:\/\/doi.org\/10.1145\/2371316.2371349.","key":"1549_CR15","DOI":"10.1145\/2371316.2371349"},{"doi-asserted-by":"publisher","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: NIPS 2012 - 25th Conference on neural information processing systems. 2012; p. 1097\u20131105. https:\/\/doi.org\/10.1145\/3065386.","key":"1549_CR16","DOI":"10.1145\/3065386"},{"key":"1549_CR17","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/537428","author":"MA Shayegan","year":"2014","unstructured":"Shayegan MA, Aghabozorgi S. A new dataset size reduction approach for PCA-based classification in OCR application. Math Probl Eng. 2014. https:\/\/doi.org\/10.1155\/2014\/537428.","journal-title":"Math Probl Eng"},{"unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N. An image is worth 16x16 words: transformers for image recognition at scale. In: Ninth International Conference on Learning Representations (ICLR) (2020). https:\/\/openreview.net\/forum?id=YicbFdNTTy.","key":"1549_CR18"},{"doi-asserted-by":"crossref","unstructured":"Kolesnikov A, Beyer L, Zhai X, Puigcerver J, Yung J, Gelly S, Houlsby N. Big Transfer (BiT): General Visual Representation Learning. In: Vedaldi A, Bischof H, Brox T, Frahm JM, editors. 16th European Conference on Computer Vision. Lecture Notes in Computer Science, vol 12350. Springer: Cham; 2020. pp. 491\u2013507.","key":"1549_CR19","DOI":"10.1007\/978-3-030-58558-7_29"},{"unstructured":"Touvron H, Vedaldi A, Douze M, J\u00e9gou H. Fixing the train-test resolution discrepancy: FixEfficientNet. Adv Neural Inf Proces Syst. 2019;32. https:\/\/papers.nips.cc\/paper\/2019\/hash\/d03a857a23b5285736c4d55e0bb067c8-Abstract.html.","key":"1549_CR20"},{"doi-asserted-by":"crossref","unstructured":"Pham H, Dai Z, Xie Q, Luong M-T, Le QV. Meta Pseudo Labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020. p. 11557\u201311568.","key":"1549_CR21","DOI":"10.1109\/CVPR46437.2021.01139"},{"doi-asserted-by":"publisher","unstructured":"Xie Q, Luong MT, Hovy E, Le QV. Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE Computer Society Conference on computer vision and pattern recognition, 2020; p. 10684\u201395. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01070","key":"1549_CR22","DOI":"10.1109\/CVPR42600.2020.01070"},{"unstructured":"Foret P, Kleiner A, Mobahi H, Neyshabur B. Sharpness-aware minimization for efficiently improving generalization. In: Ninth International Conference on learning representations (ICLR), 2020.","key":"1549_CR23"},{"unstructured":"Riquelme C, Puigcerver J, Mustafa B, Neumann M, Jenatton R, Pinto AS, Keysers D, Houlsby N. Scaling Vision with Sparse Mixture of Experts.  In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors. Advances in Neural Information Processing Systems, vol 34. Curran Associates, Inc; 2021. pp. 8583\u20138595.","key":"1549_CR24"},{"unstructured":"Ryoo MS, Piergiovanni A, Arnab A, Dehghani M, Angelova A. TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? 2021. arXiv:2106.11297","key":"1549_CR25"},{"unstructured":"Jia C, Yang Y, Xia Y, Chen Y-T, Parekh Z, Pham H, Le QV, Sung Y, Li Z, Duerig T. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In: Meila M, Zhang T, editors. Proceedings of the 38th International Conference on machine learning. Proceedings of Machine Learning Research, vol 139. PMLR; 2021. pp. 4904\u20134916.","key":"1549_CR26"},{"doi-asserted-by":"crossref","unstructured":"Dong X, Bao J, Chen D, Zhang W, Yu N, Yuan L, Chen D, Guo B. CSWin Transformer: a General Vision Transformer Backbone With Cross-Shaped Windows. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. pp. 12114\u201312124.","key":"1549_CR27","DOI":"10.1109\/CVPR52688.2022.01181"},{"doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B. Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 2021. pp. 9992\u201310002.","key":"1549_CR28","DOI":"10.1109\/ICCV48922.2021.00986"},{"unstructured":"Dai Z, Liu H, Le QV, Tan M. CoAtNet: Marrying Convolution and Attention for All Data Sizes. In: RanzatoM, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors. Advances in Neural Information Processing Systems, vol 34. Curran Associates, Inc; 2021. pp. 3965\u20133977.","key":"1549_CR29"},{"doi-asserted-by":"crossref","unstructured":"Wu H, Xiao B, Codella N, Liu M, Dai X, Yuan L, Zhang L. CvT: Introducing Convolutions to Vision Transformers. In: The International Conference on computer vision (ICCV). 2021. p. 22\u201331. https:\/\/ieeexplore.ieee.org\/document\/9710031.","key":"1549_CR30","DOI":"10.1109\/ICCV48922.2021.00009"},{"unstructured":"Tan M, Le Q. EfficientNetV2: Smaller Models and Faster Training. In: Meila M, Zhang T, editors. Proceedings of the 38th International Conference on machine learning. Proceedings of Machine Learning Research, vol 139. PMLR; 2021. pp. 10096\u201310106.","key":"1549_CR31"},{"unstructured":"Tolstikhin I, Houlsby N, Kolesnikov A, Beyer L, Zhai X, Unterthiner T, Yung J, Steiner A, Keysers D, Uszkoreit J, Lucic M, Dosovitskiy A. MLP-Mixer: An all-MLP Architecture for Vision. In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors. Advances in Neural Information Processing Systems, vol. 34.  Curran Associates, Inc; 2021. pp. 24261\u201324272.","key":"1549_CR32"},{"unstructured":"Brock A, De S, Smith SL, Simonyan K. High-performance large-scale image recognition without normalization. In: Meila M, Zhang T, editors. Proceedings of the 38th International Conference on machine learning. Proceedings of Machine Learning Research, vol 139. PMLR; 2021. pp. 1059\u20131071.","key":"1549_CR33"},{"unstructured":"LeCun Y, Cortes C, Burges C. MNIST Handwritten Digit Database. ATT Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist.  Retrieved 27 Nov 2018","key":"1549_CR34"},{"unstructured":"Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. 2017. arXiv:1708.07747.","key":"1549_CR35"},{"key":"1549_CR36","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1016\/j.neucom.2021.08.064","volume":"463","author":"A Byerly","year":"2021","unstructured":"Byerly A, Kalganova T, Dear I. No routing needed between capsules. Neurocomputing. 2021;463:545\u201353. https:\/\/doi.org\/10.1016\/j.neucom.2021.08.064.","journal-title":"Neurocomputing"},{"unstructured":"Krizhevsky A. Learning multiple layers of features from tiny images. Technical report. 2009.","key":"1549_CR37"},{"unstructured":"Howard J. Imagenette. 2018. https:\/\/github.com\/fastai\/imagenette\/.  Retrieved March 17, 2020.","key":"1549_CR38"},{"unstructured":"Van Horn G, Perona P. The Devil is in the Tails: Fine-Grained Classification in the Wild. 2017. arXiv:1709.01450.","key":"1549_CR39"},{"doi-asserted-by":"publisher","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL. Microsoft COCO: Common Objects in Context. In: European Conference on computer vision (ECCV). Springer International Publishing; 2014. pp. 740\u2013755. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48.","key":"1549_CR40","DOI":"10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"publisher","unstructured":"Liu Z, Miao Z, Zhan X, Wang J, Gong B, Yu SX. Large-scale long-tailed recognition in an open world. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), IEEE; 2019. p. 2532\u201341. https:\/\/doi.org\/10.1109\/CVPR.2019.00264.","key":"1549_CR41","DOI":"10.1109\/CVPR.2019.00264"},{"key":"1549_CR42","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","volume":"106","author":"M Buda","year":"2018","unstructured":"Buda M, Maki A, Mazurowski MA. A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 2018;106:249\u201359. https:\/\/doi.org\/10.1016\/j.neunet.2018.07.011.","journal-title":"Neural Netw"},{"unstructured":"Cao K, Wei C, Gaidon A, Arechiga N, Ma T. Learning imbalanced datasets with label-distribution-aware margin loss. In: Proceedings of the 33rd international conference on neural information processing systems. Curran Associates Inc; 2019. pp. 1567\u20131578.","key":"1549_CR43"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01549-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-022-01549-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01549-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T12:38:52Z","timestamp":1673095132000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-022-01549-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,7]]},"references-count":43,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["1549"],"URL":"https:\/\/doi.org\/10.1007\/s42979-022-01549-4","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2023,1,7]]},"assertion":[{"value":"21 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"144"}}