{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:53:12Z","timestamp":1772866392243,"version":"3.50.1"},"reference-count":112,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0140407"],"award-info":[{"award-number":["2021ZD0140407"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42327901"],"award-info":[{"award-number":["42327901"]}],"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":"publisher","award":["62276150"],"award-info":[{"award-number":["62276150"]}],"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":"publisher","award":["62321005"],"award-info":[{"award-number":["62321005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3401036","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:30:40Z","timestamp":1715707840000},"page":"8036-8055","source":"Crossref","is-referenced-by-count":14,"title":["EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-0234","authenticated-orcid":false,"given":"Yulin","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3155-1336","authenticated-orcid":false,"given":"Yang","family":"Yue","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4850-8401","authenticated-orcid":false,"given":"Rui","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5706-8784","authenticated-orcid":false,"given":"Yizeng","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-1770","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2918284"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1355"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01216"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref11","first-page":"1311","article-title":"Automated curriculum learning for neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves","year":"2017"},{"key":"ref12","first-page":"2535","article-title":"On the power of curriculum learning in training deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hacohen","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"ref14","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2563981"},{"key":"ref16","article-title":"Learning to teach","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref19","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01055"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00538"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.11.014"},{"key":"ref27","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1119"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.168"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.237"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2010.11.002"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"ref34","first-page":"5238","article-title":"Curriculum learning by transfer learning: Theory and experiments with deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Weinshall","year":"2018"},{"key":"ref35","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1112-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"ref38","first-page":"8602","article-title":"Curriculum learning by dynamic instance hardness","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhou","year":"2020"},{"key":"ref39","article-title":"InfoBatch: Lossless training speed up by unbiased dynamic data pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qin","year":"2024"},{"key":"ref40","article-title":"Minimax curriculum learning: Machine teaching with desirable difficulties and scheduled diversity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"ref42","first-page":"21 653","article-title":"Curriculum by smoothing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sinha","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.383"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_11"},{"key":"ref45","first-page":"524","article-title":"The cascade-correlation learning architecture","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fahlman","year":"1989"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00096-8"},{"key":"ref47","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bengio","year":"2006"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref49","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.306"},{"key":"ref51","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras","year":"2018"},{"key":"ref52","article-title":"Net2Net: Accelerating learning via knowledge transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2015"},{"key":"ref53","first-page":"564","article-title":"Network morphism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2988006"},{"key":"ref55","article-title":"Budgeted training for vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia","year":"2023"},{"key":"ref56","first-page":"2616","article-title":"Towards adaptive residual network training: A neural-ODE perspective","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dong","year":"2020"},{"key":"ref57","article-title":"Budgeted training: Rethinking deep neural network training under resource constraints","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref58","first-page":"10 096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref60","first-page":"8250","article-title":"Fixing the train-test resolution discrepancy","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Touvron","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref62","article-title":"A Fourier perspective on model robustness in computer vision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yin","year":"2019"},{"key":"ref63","article-title":"Improving robustness without sacrificing accuracy with patch Gaussian augmentation","author":"Lopes","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2105.07581"},{"key":"ref65","first-page":"148","article-title":"Experiments with a new boosting algorithm","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Freund","year":"1996"},{"key":"ref66","article-title":"Variance reduction in SGD by distributed importance sampling","author":"Alain","year":"2015"},{"key":"ref67","article-title":"Online batch selection for faster training of neural networks","author":"Loshchilov","year":"2015"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref69","first-page":"364","article-title":"Adaptive sampling for SGD by exploiting side information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gopal","year":"2016"},{"key":"ref70","first-page":"1932","article-title":"Self-paced boost learning for classification","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Pi","year":"2016"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081267"},{"key":"ref72","article-title":"An empirical exploration of curriculum learning for neural machine translation","author":"Zhang","year":"2018"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1123"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02004"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1968.sp008574"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141095289051"},{"key":"ref77","volume-title":"A Wavelet Tour of Signal Processing","author":"Mallat","year":"1999"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"ref80","first-page":"2432","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref81","first-page":"11 960","article-title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2021"},{"key":"ref82","first-page":"795","article-title":"Algorithms for learning kernels based on centered alignment","volume":"13","author":"Cortes","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref83","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith","year":"2019"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref85","article-title":"Adversarial AutoAugment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3052951"},{"key":"ref87","first-page":"19 088","article-title":"Improving auto-augment via augmentation-wise weight sharing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tian","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-050753-8.50042-5"},{"key":"ref90","volume-title":"Principles of Digital Image Processing: Core Algorithms","author":"Burger","year":"2010"},{"key":"ref91","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref92","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You","year":"2019"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref95","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref97","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Khosla","year":"2011"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref102","article-title":"BEit: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref104","article-title":"Efficient self-supervised vision pretraining with local masked reconstruction","author":"Chen","year":"2022"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00211"},{"key":"ref107","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref108","article-title":"MMDetection: OpenMMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref110","article-title":"MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10746266\/10530470.pdf?arnumber=10530470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:16:11Z","timestamp":1732666571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":112,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3401036","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}