{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T04:33:35Z","timestamp":1775018015285,"version":"3.50.1"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["62336004"],"award-info":[{"award-number":["62336004"]}],"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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125603"],"award-info":[{"award-number":["62125603"]}],"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":[[2024,4]]},"DOI":"10.1109\/tpami.2023.3312311","type":"journal-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T17:47:12Z","timestamp":1693936032000},"page":"1964-1980","source":"Crossref","is-referenced-by-count":21,"title":["Introspective Deep Metric Learning"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4051-4975","authenticated-orcid":false,"given":"Chengkun","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7188-3734","authenticated-orcid":false,"given":"Wenzhao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4435-1692","authenticated-orcid":false,"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"PhiGent Robotics, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_38"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00196"},{"key":"ref3","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref11","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00098"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00294"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref17","first-page":"1","article-title":"Rethinking supervised pre-training for better downstream transferring","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Feng"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"ref19","first-page":"10750","article-title":"DropBlock: A regularization method for convolutional networks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Ghiasi"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00673"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.668"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.307"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref27","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop","author":"Hinton"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00564"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.242"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref31","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ioffe"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01437"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref34","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref35","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_45"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref39","first-page":"1","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01368"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00328"},{"key":"ref42","article-title":"Self-EMD: Self-supervised object detection without ImageNet","author":"Liu","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref44","first-page":"590","article-title":"DiVA: Diverse visual feature aggregation fordeep metric learning","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Milbich"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1113"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-1015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19309-5_55"},{"key":"ref50","first-page":"1","article-title":"Modeling uncertainty with hedged instance embeddings","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oh"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848925"},{"key":"ref52","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00655"},{"key":"ref54","first-page":"8000","article-title":"MIC: Mining interclass characteristics for improved metric learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Roth"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00660"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00727"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00056"},{"key":"ref59","article-title":"Improving the generalization of supervised models","author":"Sariyildiz","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/79.974715"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00700"},{"key":"ref63","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref64","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_27"},{"key":"ref71","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref72","first-page":"1","article-title":"SaliencyMix: A saliency guided data augmentation strategy for better regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Uddin"},{"issue":"1","key":"ref73","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"Van Der Maaten","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref74","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref75","first-page":"1","article-title":"Word representations via Gaussian embedding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vilnis"},{"key":"ref76","article-title":"The Caltech-UCSD Birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_29"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.283"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00535"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00516"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"ref84","article-title":"ResNet strikes back: An improved training procedure in TIMM","author":"Wightman","year":"2021"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_44"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00240"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00550"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00659"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00495"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.94"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00877"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01616"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00974"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00016"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00920"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01185"},{"key":"ref104","first-page":"274","article-title":"Imbalance robust Softmax for deep embedding learning","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Zhu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10461350\/10239539.pdf?arnumber=10239539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T02:20:46Z","timestamp":1709864446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10239539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":104,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3312311","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":[[2024,4]]}}}