{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T16:31:37Z","timestamp":1772037097294,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,23]]},"DOI":"10.1145\/3579654.3579661","type":"proceedings-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T16:09:40Z","timestamp":1678810180000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Regularization Strength Impact on Neural Network Ensembles"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5711-1532","authenticated-orcid":false,"given":"Cedrique Rovile","family":"Njieutcheu Tassi","sequence":"first","affiliation":[{"name":"German Aerospace Center (DLR), Institute of Optical Sensor Systems, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7176-3588","authenticated-orcid":false,"given":"Anko","family":"B\u00f6rner","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Institute of Optical Sensor Systems, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7975-036X","authenticated-orcid":false,"given":"Rudolph","family":"Triebel","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Institute of Robotics and Mechatronics, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Arsenii Ashukha Alexander Lyzhov Dmitry Molchanov and Dmitry Vetrov. 2020. Pitfalls of in-domain uncertainty estimation and ensembling in deep learning. arXiv preprint arXiv:2002.06470(2020)."},{"key":"e_1_3_2_1_2_1","unstructured":"Randall Balestriero Leon Bottou and Yann LeCun. 2022. The effects of regularization and data augmentation are class dependent. arXiv preprint arXiv:2204.03632(2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00976"},{"key":"e_1_3_2_1_4_1","volume-title":"Understanding batch normalization. Advances in neural information processing systems 31","author":"Bjorck Nils","year":"2018","unstructured":"Nils Bjorck, Carla\u00a0P Gomes, Bart Selman, and Kilian\u00a0Q Weinberger. 2018. Understanding batch normalization. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_5_1","unstructured":"Sanghyuk Chun Seong\u00a0Joon Oh Sangdoo Yun Dongyoon Han Junsuk Choe and Youngjoon Yoo. 2020. An empirical evaluation on robustness and uncertainty of regularization methods. arXiv preprint arXiv:2003.03879(2020)."},{"key":"e_1_3_2_1_6_1","unstructured":"Terrance DeVries and Graham\u00a0W Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552(2017)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/648054.743935"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412733"},{"key":"e_1_3_2_1_9_1","volume-title":"international conference on machine learning. PMLR, 1050\u20131059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning. PMLR, 1050\u20131059."},{"key":"e_1_3_2_1_10_1","volume-title":"Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel","author":"Gawlikowski Jakob","year":"2021","unstructured":"Jakob Gawlikowski, Cedrique Rovile\u00a0Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, 2021. A survey of uncertainty in deep neural networks. arXiv preprint arXiv:2107.03342(2021)."},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. PMLR, 1321\u20131330","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian\u00a0Q Weinberger. 2017. On calibration of modern neural networks. In International Conference on Machine Learning. PMLR, 1321\u20131330."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00167"},{"key":"e_1_3_2_1_13_1","volume-title":"Multiple choice learning: Learning to produce multiple structured outputs. Advances in neural information processing systems 25","author":"Guzman-Rivera Abner","year":"2012","unstructured":"Abner Guzman-Rivera, Dhruv Batra, and Pushmeet Kohli. 2012. Multiple choice learning: Learning to produce multiple structured outputs. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","unstructured":"Dan Hendrycks Mantas Mazeika and Thomas Dietterich. 2018. Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606(2018)."},{"key":"e_1_3_2_1_17_1","unstructured":"Alex Hern\u00e1ndez-Garc\u00eda and Peter K\u00f6nig. 2018. Data augmentation instead of explicit regularization. arXiv preprint arXiv:1806.03852(2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44781-0_10"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.709601"},{"key":"e_1_3_2_1_20_1","unstructured":"Gao Huang Yixuan Li Geoff Pleiss Zhuang Liu John\u00a0E Hopcroft and Kilian\u00a0Q Weinberger. 2017. Snapshot ensembles: Train 1 get m for free. arXiv preprint arXiv:1704.00109(2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR, 448\u2013456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. PMLR, 448\u2013456."},{"key":"e_1_3_2_1_23_1","unstructured":"Gregory Kahn Adam Villaflor Vitchyr Pong Pieter Abbeel and Sergey Levine. 2017. Uncertainty-aware reinforcement learning for collision avoidance. arXiv preprint arXiv:1702.01182(2017)."},{"key":"e_1_3_2_1_24_1","volume-title":"What uncertainties do we need in bayesian deep learning for computer vision?Advances in neural information processing systems 30","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision?Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEM48762.2020.9160048"},{"key":"e_1_3_2_1_26_1","unstructured":"Alex Krizhevsky Geoffrey Hinton 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_27_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey\u00a0E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_1_28_1","volume-title":"A simple weight decay can improve generalization. Advances in neural information processing systems 4","author":"Krogh Anders","year":"1991","unstructured":"Anders Krogh and John Hertz. 1991. A simple weight decay can improve generalization. Advances in neural information processing systems 4 (1991)."},{"key":"e_1_3_2_1_29_1","volume-title":"Neural network ensembles, cross validation, and active learning. Advances in neural information processing systems 7","author":"Krogh Anders","year":"1995","unstructured":"Anders Krogh, Jesper Vedelsby, 1995. Neural network ensembles, cross validation, and active learning. Advances in neural information processing systems 7 (1995), 231\u2013238."},{"key":"e_1_3_2_1_30_1","volume-title":"Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems 30","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Lee Kimin","year":"2017","unstructured":"Kimin Lee, Changho Hwang, KyoungSoo Park, and Jinwoo Shin. 2017. Confident multiple choice learning. In International Conference on Machine Learning. PMLR, 2014\u20132023."},{"key":"e_1_3_2_1_33_1","unstructured":"Stefan Lee Senthil Purushwalkam Michael Cogswell David Crandall and Dhruv Batra. 2015. Why M heads are better than one: Training a diverse ensemble of deep networks. arXiv preprint arXiv:1511.06314(2015)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/930973"},{"key":"e_1_3_2_1_35_1","volume-title":"On ensemble techniques of weight-constrained neural networks. Evolving Systems","author":"Livieris E","year":"2020","unstructured":"Ioannis\u00a0E Livieris, Lazaros Iliadis, and Panagiotis Pintelas. 2020. On ensemble techniques of weight-constrained neural networks. Evolving Systems (2020), 1\u201313."},{"key":"e_1_3_2_1_36_1","unstructured":"Christos Louizos Max Welling and Diederik\u00a0P Kingma. 2017. Learning sparse neural networks through regularization. arXiv preprint arXiv:1712.01312(2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"e_1_3_2_1_38_1","unstructured":"Mohammad Moghimi Serge\u00a0J Belongie Mohammad\u00a0J Saberian Jian Yang Nuno Vasconcelos and Li-Jia Li. 2016. Boosted convolutional neural networks.. In BMVC Vol.\u00a05. 6."},{"key":"e_1_3_2_1_39_1","unstructured":"Azadeh\u00a0Sadat Mozafari Hugo\u00a0Siqueira Gomes Wilson Le\u00e3o Steeven Janny and Christian Gagn\u00e9. 2018. Attended temperature scaling: a practical approach for calibrating deep neural networks. arXiv preprint arXiv:1810.11586(2018)."},{"key":"e_1_3_2_1_40_1","unstructured":"Rafael M\u00fcller Simon Kornblith and Geoffrey\u00a0E Hinton. 2019. When does label smoothing help?. In Advances in Neural Information Processing Systems. 4694\u20134703."},{"key":"e_1_3_2_1_41_1","volume-title":"Survey: Image mixing and deleting for data augmentation. arXiv preprint arXiv:2106.07085(2021).","author":"Naveed Humza","year":"2021","unstructured":"Humza Naveed. 2021. Survey: Image mixing and deleting for data augmentation. arXiv preprint arXiv:2106.07085(2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Machine learning yearning. URL: http:\/\/www. mlyearning. org\/(96) 139","author":"Andrew Ng.","year":"2017","unstructured":"Andrew Ng. 2017. Machine learning yearning. URL: http:\/\/www. mlyearning. org\/(96) 139 (2017)."},{"key":"e_1_3_2_1_43_1","unstructured":"Yaniv Ovadia Emily Fertig Jie Ren Zachary Nado David Sculley Sebastian Nowozin Joshua Dillon Balaji Lakshminarayanan and Jasper Snoek. 2019. Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift. In Advances in Neural Information Processing Systems. 13991\u201314002."},{"key":"e_1_3_2_1_44_1","unstructured":"Kanil Patel William Beluch Dan Zhang Michael Pfeiffer and Bin Yang. 2019. On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration. arXiv preprint arXiv:1912.07458(2019)."},{"key":"e_1_3_2_1_45_1","unstructured":"Gabriel Pereyra George Tucker Jan Chorowski \u0141ukasz Kaiser and Geoffrey Hinton. 2017. Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548(2017)."},{"key":"e_1_3_2_1_46_1","volume-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers 10, 3","author":"John Platt","year":"1999","unstructured":"John Platt 1999. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers 10, 3 (1999), 61\u201374."},{"key":"e_1_3_2_1_47_1","volume-title":"Ensemble machine learning","author":"Polikar Robi","unstructured":"Robi Polikar. 2012. Ensemble learning. In Ensemble machine learning. Springer, 1\u201334."},{"key":"e_1_3_2_1_48_1","volume-title":"Early stopping-but when?In Neural Networks: Tricks of the trade","author":"Prechelt Lutz","unstructured":"Lutz Prechelt. 1998. Early stopping-but when?In Neural Networks: Tricks of the trade. Springer, 55\u201369."},{"key":"e_1_3_2_1_49_1","volume-title":"Chi","author":"Qin Yao","year":"2021","unstructured":"Yao Qin, Xuezhi Wang, Alex Beutel, and Ed Chi. 2021. Improving calibration through the relationship with adversarial robustness. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_50_1","volume-title":"Uncertainty quantification and deep ensembles. Advances in Neural Information Processing Systems 34","author":"Rahaman Rahul","year":"2021","unstructured":"Rahul Rahaman and Alexandre\u00a0H Thiery. 2021. Uncertainty quantification and deep ensembles. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00924"},{"key":"e_1_3_2_1_52_1","volume-title":"Adversarial training for free!Advances in Neural Information Processing Systems 32","author":"Shafahi Ali","year":"2019","unstructured":"Ali Shafahi, Mahyar Najibi, Mohammad\u00a0Amin Ghiasi, Zheng Xu, John Dickerson, Christoph Studer, Larry\u00a0S Davis, Gavin Taylor, and Tom Goldstein. 2019. Adversarial training for free!Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_53_1","volume-title":"Lecture Notes in Engineering and Computer Science: Proceedings of The International MultiConference of Engineers and Computer Scientists. 7\u201311","author":"Shigei Noritaka","year":"2019","unstructured":"Noritaka Shigei, Kazuki Mandai, Satoshi Sugimoto, Ryoma Takaesu, and Yoichi Ishizuka. 2019. Land-use classification using convolutional neural network with bagging and reduced categories. In Lecture Notes in Engineering and Computer Science: Proceedings of The International MultiConference of Engineers and Computer Scientists. 7\u201311."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_1_55_1","unstructured":"Changjian Shui Azadeh\u00a0Sadat Mozafari Jonathan Marek Ihsen Hedhli and Christian Gagn\u00e9. 2018. Diversity regularization in deep ensembles. arXiv preprint arXiv:1802.07881(2018)."},{"key":"e_1_3_2_1_56_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1409","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_57_1","unstructured":"Lewis Smith and Yarin Gal. 2018. Understanding measures of uncertainty for adversarial example detection. arXiv preprint arXiv:1803.08533(2018)."},{"key":"e_1_3_2_1_58_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1 (2014), 1929\u20131958."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_60_1","volume-title":"Bayesian Convolutional Neural Network: Robustly Quantify Uncertainty for Misclassifications Detection. In Mediterranean Conference on Pattern Recognition and Artificial Intelligence. Springer, 118\u2013132","author":"Tassi Njieutcheu","year":"2019","unstructured":"Njieutcheu Tassi and Cedrique Rovile. 2019. Bayesian Convolutional Neural Network: Robustly Quantify Uncertainty for Misclassifications Detection. In Mediterranean Conference on Pattern Recognition and Artificial Intelligence. Springer, 118\u2013132."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Sunil Thulasidasan Gopinath Chennupati Jeff\u00a0A Bilmes Tanmoy Bhattacharya and Sarah Michalak. 2019. On mixup training: Improved calibration and predictive uncertainty for deep neural networks. In Advances in Neural Information Processing Systems. 13888\u201313899.","DOI":"10.2172\/1525811"},{"key":"e_1_3_2_1_62_1","volume-title":"International conference on machine learning. PMLR, 1058\u20131066","author":"Wan Li","year":"2013","unstructured":"Li Wan, Matthew Zeiler, Sixin Zhang, Yann Le\u00a0Cun, and Rob Fergus. 2013. Regularization of neural networks using dropconnect. In International conference on machine learning. PMLR, 1058\u20131066."},{"key":"e_1_3_2_1_63_1","first-page":"11809","article-title":"Rethinking calibration of deep neural networks: Do not be afraid of overconfidence","volume":"34","author":"Wang Deng-Bao","year":"2021","unstructured":"Deng-Bao Wang, Lei Feng, and Min-Ling Zhang. 2021. Rethinking calibration of deep neural networks: Do not be afraid of overconfidence. Advances in Neural Information Processing Systems 34 (2021), 11809\u201311820.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_1","unstructured":"Yeming Wen Ghassen Jerfel Rafael Muller Michael\u00a0W Dusenberry Jasper Snoek Balaji Lakshminarayanan and Dustin Tran. 2020. Combining ensembles and data augmentation can harm your calibration. arXiv preprint arXiv:2010.09875(2020)."},{"key":"e_1_3_2_1_65_1","volume-title":"Bayesian deep learning and a probabilistic perspective of generalization. Advances in neural information processing systems 33","author":"Wilson G","year":"2020","unstructured":"Andrew\u00a0G Wilson and Pavel Izmailov. 2020. Bayesian deep learning and a probabilistic perspective of generalization. Advances in neural information processing systems 33 (2020), 4697\u20134708."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26532-2_6"},{"key":"e_1_3_2_1_67_1","unstructured":"Xixin Wu and Mark Gales. 2021. Should ensemble members be calibrated?arXiv preprint arXiv:2101.05397(2021)."},{"key":"e_1_3_2_1_68_1","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747(2017)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3041525"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-006-0663-2"},{"key":"e_1_3_2_1_71_1","unstructured":"Zhilu Zhang Adrian\u00a0V Dalca and Mert\u00a0R Sabuncu. 2019. Confidence calibration for convolutional neural networks using structured dropout. arXiv preprint arXiv:1906.09551(2019)."}],"event":{"name":"ACAI 2022: 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","location":"Sanya China","acronym":"ACAI 2022"},"container-title":["Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579661","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579654.3579661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T06:59:38Z","timestamp":1755845978000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":71,"alternative-id":["10.1145\/3579654.3579661","10.1145\/3579654"],"URL":"https:\/\/doi.org\/10.1145\/3579654.3579661","relation":{},"subject":[],"published":{"date-parts":[[2022,12,23]]},"assertion":[{"value":"2023-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}