{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T04:51:01Z","timestamp":1785732661822,"version":"3.56.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276052"],"award-info":[{"award-number":["62276052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3394511","type":"journal-article","created":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T13:26:27Z","timestamp":1715347587000},"page":"7711-7724","source":"Crossref","is-referenced-by-count":6,"title":["Feature Noise Boosts DNN Generalization Under Label Noise"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6162-1295","authenticated-orcid":false,"given":"Lu","family":"Zeng","sequence":"first","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4934-0850","authenticated-orcid":false,"given":"Xiaoshuang","family":"Shi","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng","family":"Tao Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref2","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. ICML","author":"Jiang"},{"key":"ref3","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren"},{"key":"ref4","first-page":"1919","article-title":"Meta-Weight-Net: Learning an explicit mapping for sample weighting","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref6","first-page":"7260","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Yao"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101759"},{"key":"ref8","article-title":"Deep learning is robust to massive label noise","author":"Rolnick","year":"2017","journal-title":"arXiv:1705.10694"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00302"},{"key":"ref11","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref12","article-title":"The alignment property of SGD noise and how it helps select flat minima: A stability analysis","author":"Wu","year":"2022","journal-title":"arXiv:2207.02628"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2784440"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820839"},{"key":"ref15","article-title":"Towards understanding the role of over-parametrization in generalization of neural networks","author":"Neyshabur","year":"2018","journal-title":"arXiv:1805.12076"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3a74"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3243521"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref19","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref20","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. ICML","author":"Yu"},{"key":"ref21","first-page":"4313","article-title":"Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Li"},{"key":"ref22","first-page":"24392","article-title":"Understanding and improving early stopping for learning with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bai"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17319"},{"key":"ref24","first-page":"13276","article-title":"A Fourier perspective on model robustness in computer vision","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Yin"},{"key":"ref25","first-page":"20","article-title":"Explaining and harnessing adversarial examples","volume":"1050","author":"Goodfellow","year":"2015","journal-title":"Stat"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref27","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen"},{"key":"ref28","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016","journal-title":"arXiv:1609.04836"},{"key":"ref29","article-title":"Implicit regularization of dropout","author":"Zhang","year":"2022","journal-title":"arXiv:2207.05952"},{"key":"ref30","article-title":"A PAC-Bayesian tutorial with a dropout bound","author":"McAllester","year":"2013","journal-title":"arXiv:1307.2118"},{"key":"ref31","first-page":"1377","article-title":"Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of entropy-SGD and data-dependent priors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dziugaite"},{"key":"ref32","first-page":"831","article-title":"Principles of risk minimization for learning theory","volume-title":"Proc. 4th Int. Conf. Neural Inf. Process. Syst.","author":"Vapnik"},{"issue":"3","key":"ref33","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1023\/A:1007618624809","article-title":"Some PAC-Bayesian theorems","volume":"37","author":"McAllester","year":"1999","journal-title":"Mach. Learn."},{"key":"ref34","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"Dziugaite","year":"2017","journal-title":"arXiv:1703.11008"},{"key":"ref35","first-page":"4093","article-title":"How tight can PAC-Bayes be in the small data regime?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Foong"},{"key":"ref36","first-page":"2521","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","volume-title":"Proc. NeurIPS","author":"Xu"},{"key":"ref37","first-page":"5949","article-title":"Exploring generalization in deep learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Neyshabur"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01403"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503149"},{"key":"ref40","first-page":"4071","article-title":"Improving generalization by controlling label-noise information in neural network weights","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Harutyunyan"},{"key":"ref41","article-title":"A primer on PAC-Bayesian learning","author":"Guedj","year":"2019","journal-title":"arXiv:1901.05353"},{"key":"ref42","volume-title":"Elements of Information Theory","author":"Thomas","year":"2006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/34.120331"},{"key":"ref44","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2019","journal-title":"arXiv:1907.07484"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref46","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref47","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Vinyals"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.21049"},{"key":"ref49","volume-title":"LeNet-5, Convolutional Neural Networks","author":"LeCun","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref52","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013","journal-title":"arXiv:1312.6034"},{"key":"ref53","article-title":"MLclf: The project machine learning CLassiFication for utilizing mini-ImageNet and tiny-ImageNet","author":"Cao","year":"2022","journal-title":"Zenodo"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01400"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10528353.pdf?arnumber=10528353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:15Z","timestamp":1765219275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10528353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":55,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3394511","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}