{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T02:17:40Z","timestamp":1768529860827,"version":"3.49.0"},"reference-count":26,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"am","delay-in-days":644,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1016\/j.neunet.2024.106753","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T05:52:58Z","timestamp":1727675578000},"page":"106753","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Optimal layer selection for latent data augmentation"],"prefix":"10.1016","volume":"181","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6974-8103","authenticated-orcid":false,"given":"Tomoumi","family":"Takase","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Karakida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2024.106753_bib0002","series-title":"Thirty-seventh Conference on Neural Information Processing Systems","article-title":"DP-Mix: mixup-based data augmentation for differentially private learning","author":"Bao","year":"2023"},{"key":"10.1016\/j.neunet.2024.106753_bib0008","series-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIX","first-page":"694","article-title":"Feature space augmentation for long-tailed data","author":"Chu","year":"2020"},{"key":"10.1016\/j.neunet.2024.106753_bib0013","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"113","article-title":"AutoAugment: learning augmentation strategies from data","author":"Cubuk","year":"2019"},{"key":"10.1016\/j.neunet.2024.106753_bib0018","series-title":"Advances in Neural Information Processing Systems, Vol. 33","first-page":"18613","article-title":"RandAugment: practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"10.1016\/j.neunet.2024.106753_bib0007","unstructured":"T. DeVries, G.W. Taylor, Dataset augmentation in feature space, arXiv:1702.05538 [cs, stat] (Feb. 2017)."},{"key":"10.1016\/j.neunet.2024.106753_bib0012","unstructured":"T. DeVries, G.W. Taylor, Improved Regularization of convolutional neural networks with cutout, arXiv:1708.04552 [cs] (Nov. 2017). doi:10.48550\/arXiv.1708.04552."},{"key":"10.1016\/j.neunet.2024.106753_bib0009","unstructured":"X. Gastaldi, Shake-shake regularization, arXiv:1705.07485 [cs] (May 2017). 10.48550\/arXiv.1705.07485."},{"key":"10.1016\/j.neunet.2024.106753_bib0011","series-title":"32nd Conference on Neural Information Processing Systems (NeurIPS 2018)","article-title":"DropBlock: A regularization method for convolutional networks","author":"Ghiasi","year":"2018"},{"key":"10.1016\/j.neunet.2024.106753_bib0024","series-title":"2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"3535","article-title":"Meta Approach to Data Augmentation Optimization","author":"Hataya","year":"2022"},{"key":"10.1016\/j.neunet.2024.106753_bib0003","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1717","article-title":"When to Learn What: Model-Adaptive Data Augmentation Curriculum","author":"Hou","year":"2023"},{"key":"10.1016\/j.neunet.2024.106753_bib0006","series-title":"IEEE\/CVF International Conference on Computer Vision","first-page":"8886","article-title":"A Simple feature augmentation for domain generalization","author":"Li","year":"2021"},{"key":"10.1016\/j.neunet.2024.106753_bib0017","series-title":"Advances in Neural Information Processing Systems","first-page":"6665","volume":"32","author":"Lim","year":"2019"},{"key":"10.1016\/j.neunet.2024.106753_bib0019","unstructured":"T.C. LingChen, A. Khonsari, A. Lashkari, M.R. Nazari, J.S. Sambee, M.A. Nascimento, UniformAugment: a search-free probabilistic data augmentation approach, arXiv:2003.14348 [cs] (Mar. 2020). doi:10.48550\/arXiv.2003.14348."},{"key":"10.1016\/j.neunet.2024.106753_bib0014","series-title":"Computer vision \u2013 eccv 2018","first-page":"19","article-title":"Progressive Neural Architecture Search","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2024.106753_bib0026","series-title":"International Conference on Artificial Intelligence and Statistics","article-title":"Optimizing millions of hyperparameters by implicit differentiation","author":"Lorraine","year":"2020"},{"key":"10.1016\/j.neunet.2024.106753_bib0025","unstructured":"J. Luketina, M. Berglund, K. Greff, T. Raiko. (2016). Scalable gradient-based tuning of continuous regularization hyperparameters, In: International Conference on Machine Learning (ICML)."},{"key":"10.1016\/j.neunet.2024.106753_bib0020","series-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"774","article-title":"TrivialAugment: tuning-free yet state-of-the-art data augmentation","author":"M\u00a8uller","year":"2021"},{"issue":"11","key":"10.1016\/j.neunet.2024.106753_bib0021","doi-asserted-by":"crossref","first-page":"9351","DOI":"10.1609\/aaai.v35i11.17127","article-title":"AutoDropout: learning dropout patterns to regularize deep networks","volume":"35","author":"Pham","year":"2021","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2024.106753_bib0015","series-title":"35th International Conference on Machine Learning, PMLR","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","author":"Pham","year":"2018"},{"key":"10.1016\/j.neunet.2024.106753_bib0022","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.neucom.2021.02.080","article-title":"Self-paced data augmentation for training neural networks","volume":"442","author":"Takase","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2024.106753_bib0023","series-title":"Computer vision \u2013 eccv 2020, vol. 12352","first-page":"313","article-title":"OnlineAugment: Online Data Augmentation with Less Domain Knowledge","author":"Tang","year":"2020"},{"key":"10.1016\/j.neunet.2024.106753_bib0004","series-title":"36th International Conference on Machine Learning","article-title":"Better representations by interpolating hidden states","author":"Verma","year":"2019"},{"key":"10.1016\/j.neunet.2024.106753_bib0010","doi-asserted-by":"crossref","unstructured":"Y. Yamada, M. Iwamura, T. Akiba, K. Kise, Shakedrop regularization for deep residual learning, IEEE Access 7 (2019) 186126\u2013186136, conference Name: IEEE Access. 10.1109\/ACCESS.2019.2960566.","DOI":"10.1109\/ACCESS.2019.2960566"},{"key":"10.1016\/j.neunet.2024.106753_bib0001","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6022","article-title":"CutMix: regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"10.1016\/j.neunet.2024.106753_bib0005","series-title":"International Conference on Learning Representations","article-title":"mixup: beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neunet.2024.106753_bib0016","unstructured":"B. Zoph, Q. Le, Neural architecture search with reinforcement learning, in: International Conference on Learning Representations, 2022."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024006774?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024006774?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T02:20:32Z","timestamp":1750126832000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608024006774"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":26,"alternative-id":["S0893608024006774"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2024.106753","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Optimal layer selection for latent data augmentation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2024.106753","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106753"}}