{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T14:10:59Z","timestamp":1783865459587,"version":"3.55.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62222607"],"award-info":[{"award-number":["62222607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3591018","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T18:08:29Z","timestamp":1753121309000},"page":"9922-9937","source":"Crossref","is-referenced-by-count":2,"title":["Sel4FT: Annotation Selection for Pretraining-Finetuning With Distribution Shift"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1782-5127","authenticated-orcid":false,"given":"Han","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-8795","authenticated-orcid":false,"given":"Yichen","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6556-8359","authenticated-orcid":false,"given":"Mingyu","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1474-1200","authenticated-orcid":false,"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-7679","authenticated-orcid":false,"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_9"},{"key":"ref2","article-title":"BEIT: BRRT pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00188"},{"key":"ref5","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref6","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00521"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref12","article-title":"Selection via proxy: Efficient data selection for deep learning","author":"Coleman","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref15","first-page":"6565","article-title":"Scaling up dataset distillation to imagenet-1 k with constant memory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cui"},{"key":"ref16","first-page":"34391","article-title":"Remember the past: Distilling datasets into addressable memories for neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Deng"},{"key":"ref17","article-title":"Adversarial active learning for deep networks: A margin based approach","author":"Ducoffe","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1063"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_37"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref21","article-title":"Towards lossless dataset distillation via difficulty-aligned trajectory matching","author":"Guo","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00343"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3336525"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206627"},{"key":"ref29","first-page":"5464","article-title":"Grad-match: Gradient matching based data subset selection for efficient deep model training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Killamsetty"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00807"},{"key":"ref31","article-title":"A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref32","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref33","first-page":"12352","article-title":"Dataset condensation with contrastive signals","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937632"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50026-X"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01588"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00914"},{"key":"ref39","first-page":"13877","article-title":"Efficient dataset distillation using random feature approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Loo"},{"key":"ref40","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2017"},{"key":"ref41","first-page":"728","article-title":"Latent structured active learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_65"},{"key":"ref43","article-title":"Low budget active learning via wasserstein distance: An integer programming approach","author":"Mahmood","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.51"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093556"},{"key":"ref46","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mirzasoleiman"},{"key":"ref47","article-title":"Parting with illusions about deep active learning","author":"Mittal","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487138"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01192"},{"key":"ref50","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Paul"},{"key":"ref51","article-title":"Infobatch: Lossless training speed up by unbiased dynamic data pruning","author":"Qin","year":"2023"},{"key":"ref52","article-title":"Accelerating deep learning with dynamic data pruning","author":"Raju","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710701"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01568"},{"key":"ref58","article-title":"Active learning for convolutional neural networks: A core-set approach","author":"Sener"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01581"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref62","article-title":"An empirical study of example forgetting during deep neural network learning","author":"Toneva","year":"2018"},{"key":"ref63","first-page":"45","article-title":"Support vector machine active learning with applications to text classification","volume":"2","author":"Tong","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref65","article-title":"Representation learning with contrastive predictive coding","author":"Van den Oord","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2589879"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01188"},{"key":"ref68","article-title":"Dataset distillation","author":"Wang","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02271"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_34"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00018"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3323376"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00529"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref78","article-title":"Navigating complexity: Toward lossless graph condensation via expanding window matching","author":"Zhang","year":"2024"},{"key":"ref79","first-page":"12674","article-title":"Dataset condensation with differentiable siamese augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00645"},{"key":"ref81","article-title":"Dataset condensation with gradient matching","author":"Zhao","year":"2020"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00759"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref85","article-title":"iBOT: Image bert pre-training with online tokenizer","author":"Zhou","year":"2021"},{"key":"ref86","first-page":"9813","article-title":"Dataset distillation using neural feature regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref87","article-title":"Generative adversarial active learning","author":"Zhu","year":"2017"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11086491.pdf?arnumber=11086491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:07Z","timestamp":1759772227000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11086491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":87,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3591018","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":[[2025,11]]}}}