{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:20:15Z","timestamp":1774628415137,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2020MF093"],"award-info":[{"award-number":["ZR2020MF093"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Scientific and Technological Projects of CNPC","award":["ZD2019-183-003"],"award-info":[{"award-number":["ZD2019-183-003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s11063-022-10885-8","type":"journal-article","created":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T13:04:00Z","timestamp":1654088640000},"page":"345-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Knowledge Reverse Distillation Based Confidence Calibration for Deep Neural Networks"],"prefix":"10.1007","volume":"55","author":[{"given":"Xianhui","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9316-9539","authenticated-orcid":false,"given":"Xiaogang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,1]]},"reference":[{"key":"10885_CR1","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. Int Conf Mach Learn PMLR 448\u2013456"},{"issue":"1","key":"10885_CR2","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"10885_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594","author":"C Szegedy","year":"2015","unstructured":"Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. Proc IEEE Conf Comput Vis Pattern Recognit. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"10885_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130191","author":"J Gui","year":"2021","unstructured":"Gui J, Sun Z, Wen Y et al (2021) A review on generative adversarial networks: Algorithms, theory, and applications. IEEE Trans Knowl Data Eng in press. https:\/\/doi.org\/10.1109\/TKDE.2021.3130191","journal-title":"IEEE Trans Knowl Data Eng in press"},{"key":"10885_CR5","unstructured":"Huang Q, Zhang H, Song J, et al (2021) A survey of deep learning for low-shot object detection. arXiv:2112.02814"},{"key":"10885_CR6","doi-asserted-by":"publisher","first-page":"68675","DOI":"10.1109\/ACCESS.2021.3077350","volume":"9","author":"S Singh","year":"2021","unstructured":"Singh S, Mahmood A (2021) The NLP cookbook: modern recipes for transformer based deep learning architectures. IEEE Access 9:68675\u201368702","journal-title":"IEEE Access"},{"key":"10885_CR7","unstructured":"Jozefowicz R, Vinyals O, Schuster M, et al (2016) Exploring the limits of language modeling. arXiv:1602.02410"},{"key":"10885_CR8","doi-asserted-by":"crossref","unstructured":"Li J (2021) Recent advances in end-to-end automatic speech recognition. arXiv:2111.01690","DOI":"10.1561\/116.00000050"},{"key":"10885_CR9","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. arXiv:1406.2199"},{"issue":"2","key":"10885_CR10","first-page":"1","volume":"54","author":"G Pang","year":"2021","unstructured":"Pang G, Shen C, Cao L et al (2021) Deep learning for anomaly detection: a review. ACM Comput Surv CSUR 54(2):1\u201338","journal-title":"ACM Comput Surv CSUR"},{"key":"10885_CR11","unstructured":"Amodei D, Olah C, Steinhardt J, et al (2016) Concrete problems in AI safety. arXiv:1606.06565"},{"key":"10885_CR12","unstructured":"Brundage M, Avin S, Clark J. et al (2018). The malicious use of artificial intelligence: Forecasting, prevention, and mitigation. arXiv:1802.07228"},{"key":"10885_CR13","unstructured":"Michelmore R, Kwiatkowska M, Gal Y (2018) Evaluating uncertainty quantification in end-to-end autonomous driving control. arXiv:1811.06817"},{"key":"10885_CR14","unstructured":"Bojarski M, Del Testa D, Dworakowski D, et al (2016) End to end learning for self-driving cars. arXiv:1604.07316"},{"issue":"2","key":"10885_CR15","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1136\/amiajnl-2011-000291","volume":"19","author":"X Jiang","year":"2012","unstructured":"Jiang X, Osl M, Kim J et al (2012) Calibrating predictive model estimates to support personalized medicine. J Am Med Inf Assoc 19(2):263\u2013274. https:\/\/doi.org\/10.1136\/amiajnl-2011-000291","journal-title":"J Am Med Inf Assoc"},{"key":"10885_CR16","unstructured":"Pleiss G, Raghavan M, Wu F, et al (2017) On fairness and calibration. arXiv:1709.02012"},{"key":"10885_CR17","first-page":"609","volume":"1","author":"B Zadrozny","year":"2001","unstructured":"Zadrozny B, Elkan C (2001) Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers. Inte Conf Mach Learn PMLR 1:609\u2013616","journal-title":"Inte Conf Mach Learn PMLR"},{"key":"10885_CR18","doi-asserted-by":"publisher","unstructured":"Zadrozny B, Elkan C (2002) Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 694\u2013699. https:\/\/doi.org\/10.1145\/775107.775151","DOI":"10.1145\/775107.775151"},{"issue":"3","key":"10885_CR19","first-page":"61","volume":"10","author":"J Platt","year":"1999","unstructured":"Platt J (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers 10(3):61\u201374","journal-title":"Advances in large margin classifiers"},{"key":"10885_CR20","unstructured":"Guo C, Pleiss G, Sun Y, et al (2017) On calibration of modern neural networks. Int Conf Mach Learn PMLR 1321\u20131330"},{"key":"10885_CR21","first-page":"1","volume":"99","author":"K Fernando","year":"2021","unstructured":"Fernando K, Ruwani M, Tsokos Chris P (2021) Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks. IEEE Trans Neural Netw Learn Syst 99:1\u201312","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10885_CR22","unstructured":"Pereyra G, Tucker G, Chorowski J, et al (2017) Regularizing neural networks by penalizing confident output distributions. arXiv:1701.06548"},{"key":"10885_CR23","unstructured":"Kumar A, Sarawagi S, Jain U (2018) Trainable calibration measures for neural networks from kernel mean embeddings. Int Conf Mach Learn PMLR 2805\u20132814"},{"key":"10885_CR24","unstructured":"DeVries T, Taylor GW (2018) Learning confidence for out-of-distribution detection in neural networks. arXiv:1802.04865"},{"key":"10885_CR25","doi-asserted-by":"crossref","unstructured":"Ji B, Jung H, Yoon J, et al (2019) Bin-wise temperature scaling: improvement in confidence calibration performance through simple scaling techniques. In: 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW). IEEE, pp 4190\u20134196","DOI":"10.1109\/ICCVW.2019.00515"},{"key":"10885_CR26","doi-asserted-by":"crossref","unstructured":"Seo S, Seo PH, Han B (2019) Learning for single-shot confidence calibration in deep neural networks through stochastic inferences. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9030\u20139038","DOI":"10.1109\/CVPR.2019.00924"},{"key":"10885_CR27","unstructured":"Zhang Z, Dalca AV, Sabuncu MR (2019) Confidence calibration for convolutional neural networks using structured dropout. arXiv:1906.09551"},{"key":"10885_CR28","doi-asserted-by":"publisher","unstructured":"Huang G, Sun Y, Liu Z, et al (2016) Deep networks with stochastic depth. In: European conference on computer vision. Springer, Cham, pp 646\u2013661. https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39","DOI":"10.1007\/978-3-319-46493-0_39"},{"issue":"1\u20132","key":"10885_CR29","first-page":"12","volume":"32","author":"MH DeGroot","year":"1983","unstructured":"DeGroot MH, Fienberg SE (1983) The comparison and evaluation of forecasters. J Roy Stat Soc Ser D (The Statistician) 32(1\u20132):12\u201322","journal-title":"J Roy Stat Soc Ser D (The Statistician)"},{"key":"10885_CR30","doi-asserted-by":"publisher","unstructured":"Bucila C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: ACM SIGKDD international conference on knowledge discovery and data mining. Computer Science Cornell University. https:\/\/doi.org\/10.1145\/1150402.1150464","DOI":"10.1145\/1150402.1150464"},{"key":"10885_CR31","first-page":"1","volume":"99","author":"L Wang","year":"2021","unstructured":"Wang L, Yoon KJ (2021) Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks. IEEE Trans Pattern Anal Mach Intell 99:1","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10885_CR32","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images. Master\u2019s thesis, Department of Computer Science, University of Toronto"},{"key":"10885_CR33","unstructured":"Netzer Y, Wang T, Coates A, Bissacco A, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. NIPS workshop on deep learning and unsupervised feature learning"},{"issue":"11","key":"10885_CR34","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 et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"key":"10885_CR35","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, et al (2018) ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. IEEE, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"10885_CR36","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"10885_CR37","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"10885_CR38","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, et al. (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"10885_CR39","unstructured":"Zhang J, Kailkhura B, Han TYJ (2020) Mix-n-match: ensemble and compositional methods for uncertainty calibration in deep learning. In: International conference on machine learning, pp 11117\u201311128"},{"key":"10885_CR40","unstructured":"Bohdal O, Yang Y, Hospedales T (2021) Meta-calibration: meta-learning of model calibration using differentiable expected calibration error. arXiv:2106.09613"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10885-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10885-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10885-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T14:22:36Z","timestamp":1678112556000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10885-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["10885"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10885-8","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,1]]},"assertion":[{"value":"7 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2022","order":2,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}