{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:56:05Z","timestamp":1783526165471,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160403"],"award-info":[{"award-number":["2022ZD0160403"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176178"],"award-info":[{"award-number":["62176178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3478854","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:51:27Z","timestamp":1729187487000},"page":"6029-6044","source":"Crossref","is-referenced-by-count":10,"title":["NTK-Guided Few-Shot Class Incremental Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0163-4105","authenticated-orcid":false,"given":"Jingren","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-3739","authenticated-orcid":false,"given":"Zhong","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0294-2099","authenticated-orcid":false,"given":"Yunlong","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200865"},{"key":"ref6","first-page":"1","article-title":"On the soft-subnetwork for few-shot class incremental learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yoon"},{"key":"ref7","first-page":"1","article-title":"Neural collapse inspired feature-classifier alignment for few-shot class-incremental learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref8","first-page":"17018","article-title":"Fast finite width neural tangent kernel","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Novak"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ad65df"},{"key":"ref10","first-page":"8571","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jacot"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00957"},{"key":"ref12","article-title":"Over-parameterised shallow neural networks with asymmetrical node scaling: Global convergence guarantees and feature learning","author":"Caron","year":"2023","journal-title":"arXiv:2302.01002"},{"key":"ref13","article-title":"Gradient descent provably optimizes over-parameterized neural networks","author":"Du","year":"2018","journal-title":"arXiv:1810.02054"},{"key":"ref14","article-title":"Stochastic gradient descent optimizes over-parameterized deep ReLU networks","author":"Zou","year":"2018","journal-title":"arXiv:1811.08888"},{"key":"ref15","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref16","first-page":"23549","article-title":"More than a toy: Random matrix models predict how real-world neural representations generalize","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref17","first-page":"8609","article-title":"Stability & generalisation of gradient descent for shallow neural networks without the neural tangent kernel","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Richards"},{"key":"ref18","article-title":"How spurious features are memorized: Precise analysis for random and NTK features","author":"Bombari","year":"2023","journal-title":"arXiv:2305.12100"},{"key":"ref19","article-title":"Generalization and stability of interpolating neural networks with minimal width","author":"Taheri","year":"2023","journal-title":"arXiv:2302.09235"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0_2"},{"key":"ref21","first-page":"404","article-title":"Continuous neural networks","author":"Le Roux","year":"2007","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref22","article-title":"Steps toward deep kernel methods from infinite neural networks","author":"Hazan","year":"2015","journal-title":"arXiv:1508.05133"},{"key":"ref23","first-page":"1655","article-title":"Width provably matters in optimization for deep linear neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref24","first-page":"15156","article-title":"Finite versus infinite neural networks: An empirical study","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lee"},{"key":"ref25","article-title":"TKIL: Tangent kernel approach for class balanced incremental learning","author":"Xiang","year":"2022","journal-title":"arXiv:2206.08492"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"ref27","first-page":"6747","article-title":"Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima","volume-title":"Proc. 35th Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Shi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00885"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3236160"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00884"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_22"},{"key":"ref32","first-page":"8572","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lee"},{"key":"ref33","article-title":"Tensor programs II: Neural tangent kernel for any architecture","author":"Yang","year":"2020","journal-title":"arXiv:2006.14548"},{"key":"ref34","first-page":"322","article-title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Arora"},{"key":"ref35","first-page":"2937","article-title":"On lazy training in differentiable programming","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Chizat"},{"key":"ref36","first-page":"2422","article-title":"SGD learns the conjugate kernel class of the network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Daniely"},{"key":"ref37","article-title":"Towards understanding the role of over-parametrization in generalization of neural networks","author":"Neyshabur","year":"2018","journal-title":"arXiv:1805.12076"},{"key":"ref38","first-page":"2269","article-title":"Implicit regularization via neural feature alignment","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Baratin"},{"key":"ref39","article-title":"An exponential learning rate schedule for deep learning","author":"Li","year":"2019","journal-title":"arXiv:1910.07454"},{"key":"ref40","article-title":"Bayesian deep convolutional networks with many channels are Gaussian processes","author":"Novak","year":"2018","journal-title":"arXiv:1810.05148"},{"key":"ref41","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019","journal-title":"arXiv:1912.02757"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23103-1"},{"key":"ref43","first-page":"1072","article-title":"A theoretical analysis of catastrophic forgetting through the NTK overlap matrix","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Doan"},{"key":"ref44","first-page":"279","article-title":"Generalization errors and learning curves for regression with multi-task Gaussian processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Chai"},{"key":"ref45","article-title":"Generalisation guarantees for continual learning with orthogonal gradient descent","author":"Abbana Bennani","year":"2020","journal-title":"arXiv:2006.11942"},{"key":"ref46","first-page":"8119","article-title":"Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref47","article-title":"Characterizing the spectrum of the NTK via a power series expansion","author":"Murray","year":"2022","journal-title":"arXiv:2211.07844"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01377"},{"key":"ref49","first-page":"9712","article-title":"Regularization matters: Generalization and optimization of neural nets vs their induced kernel","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wei"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01710"},{"key":"ref51","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NIPS","author":"Caron"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref58","first-page":"1","article-title":"Designing BERT for convolutional networks: Sparse and hierarchical masked modeling","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tian"},{"key":"ref59","first-page":"27267","article-title":"Margin-based few-shot class-incremental learning with class-level overfitting mitigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zou"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref61","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref62","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref67","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref69","first-page":"1","article-title":"AugMix: A simple method to improve robustness and uncertainty under data shift","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref70","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00748"},{"key":"ref72","first-page":"1","article-title":"Warping the space: Weight space rotation for class-incremental few-shot learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01931"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10721322.pdf?arnumber=10721322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:59:38Z","timestamp":1732669178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10721322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3478854","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}