{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:36:35Z","timestamp":1784212595071,"version":"3.55.0"},"reference-count":119,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0140407"],"award-info":[{"award-number":["2021ZD0140407"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62022048"],"award-info":[{"award-number":["62022048"]}],"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\/100020721","name":"Guoqiang Institute, Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020721","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3364500","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T18:00:53Z","timestamp":1714068053000},"page":"3130-3144","source":"Crossref","is-referenced-by-count":54,"title":["Fine-Grained Recognition With Learnable Semantic Data Augmentation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0404-1737","authenticated-orcid":false,"given":"Yifan","family":"Pu","sequence":"first","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-0234","authenticated-orcid":false,"given":"Yulin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junlan","family":"Feng","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Deng","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The Caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref3","article-title":"Novel dataset for fine-grained image categorization","volume-title":"Proc. CVPR Workshops","author":"Khosla"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3513-y"},{"key":"ref6","article-title":"Products-10K: A large-scale product recognition dataset","author":"Bai","year":"2020","journal-title":"arXiv:2008.10545"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-017-1053-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2018.8652307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196959"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref13","first-page":"11960","article-title":"Not all images are worth 16\u00d716 words: Dynamic transformers for efficient image recognition","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref14","first-page":"2432","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref15","first-page":"36845","article-title":"Latency-aware spatial-wise dynamic networks","volume-title":"Proc. NeurIPS","author":"Han"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_22"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00606"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00551"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref24","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00538"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref28","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref30","first-page":"12635","article-title":"Implicit semantic data augmentation for deep networks","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref31","article-title":"Deep learning for fine-grained image analysis: A survey","author":"Wei","year":"2019","journal-title":"arXiv:1907.03069"},{"key":"ref32","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref35","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref37","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.12.049"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055617"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107164"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2637331"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439285"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00163"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2839528"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_22"},{"key":"ref62","first-page":"4277","article-title":"Learning deep bilinear transformation for fine-grained image representation","volume-title":"Proc. NeurIPS","author":"Zheng"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2977457"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413638"},{"key":"ref65","first-page":"635","article-title":"Maximum-entropy fine grained classification","volume-title":"Proc. NeurIPS","author":"Dubey"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6882"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00783"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref70","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"Perez","year":"2017","journal-title":"arXiv:1712.04621"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628742"},{"key":"ref72","article-title":"Data augmentation by pairing samples for images classification","author":"Inoue","year":"2018","journal-title":"arXiv:1801.02929"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00139"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2935128"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/IIPHDW.2018.8388338"},{"key":"ref76","article-title":"Dataset augmentation in feature space","volume-title":"Proc. ICLR Workshop","author":"DeVries"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"ref78","article-title":"GAN augmentation: Augmenting training data using generative adversarial networks","author":"Bowles","year":"2018","journal-title":"arXiv:1810.10863"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00146"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683197"},{"key":"ref81","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. ICML","author":"Verma"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263112"},{"key":"ref83","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00517"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01135"},{"key":"ref86","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. ICML","author":"Finn"},{"key":"ref87","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","volume-title":"Proc. ICML","author":"Franceschi"},{"key":"ref88","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC49280.2020.9152261"},{"key":"ref90","article-title":"Meta-learning update rules for unsupervised representation learning","volume-title":"Proc. ICLR","author":"Metz"},{"key":"ref91","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"1611","journal-title":"arXiv:1611.02779"},{"key":"ref92","first-page":"5405","article-title":"Evolved policy gradients","volume-title":"Proc. NeurIPS","author":"Houthooft"},{"key":"ref93","article-title":"Meta-learning curiosity algorithms","volume-title":"Proc. ICLR","author":"Alet"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref95","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. ICLR","author":"Zoph"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-013-9406-y"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref98","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. ICLR","author":"Ravi"},{"key":"ref99","article-title":"A simple neural attentive meta-learner","volume-title":"Proc. ICLR","author":"Mishra"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3114536"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref102","first-page":"3988","article-title":"Learning to learn by gradient descent by gradient descent","volume-title":"Proc. NeurIPS","author":"Andrychowicz"},{"key":"ref103","first-page":"1919","article-title":"Meta-weight-Net: Learning an explicit mapping for sample weighting","volume-title":"Proc. NeurIPS","author":"Shu"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00977"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126668"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197931"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109305"},{"issue":"11","key":"ref116","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref118","first-page":"2283","article-title":"Stochastic majorization-minimization algorithms for large-scale optimization","volume-title":"Proc. NeurIPS","author":"Mairal"},{"key":"ref119","volume-title":"Nonlinear Programming","author":"Bertsekas","year":"2016"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10508756.pdf?arnumber=10508756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T19:14:04Z","timestamp":1714763644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":119,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3364500","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}