{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:22:05Z","timestamp":1773840125032,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["U20B2066"],"award-info":[{"award-number":["U20B2066"]}],"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":["61976186"],"award-info":[{"award-number":["61976186"]}],"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":["62106220"],"award-info":[{"award-number":["62106220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007834","name":"Ningbo Natural Science Foundation","doi-asserted-by":"publisher","award":["2021J189"],"award-info":[{"award-number":["2021J189"]}],"id":[{"id":"10.13039\/100007834","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study","doi-asserted-by":"publisher","award":["SN-ZJU-SIAS-001"],"award-info":[{"award-number":["SN-ZJU-SIAS-001"]}],"id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021FZZX001-23"],"award-info":[{"award-number":["2021FZZX001-23"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3263105","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:44:20Z","timestamp":1680543860000},"page":"2093-2106","source":"Crossref","is-referenced-by-count":19,"title":["Knowledge Amalgamation for Object Detection With Transformers"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3247-6356","authenticated-orcid":false,"given":"Haofei","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6171-3168","authenticated-orcid":false,"given":"Feng","family":"Mao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Xixi Campus, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4936-4887","authenticated-orcid":false,"given":"Mengqi","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Computer and Computing Science, Hangzhou City University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongfan","family":"Fang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8640-8434","authenticated-orcid":false,"given":"Zunlei","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Software Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3671-6521","authenticated-orcid":false,"given":"Jie","family":"Song","sequence":"additional","affiliation":[{"name":"College of Software Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2621-6048","authenticated-orcid":false,"given":"Mingli","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Institute for Advanced Study, Zhejiang University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref3","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref4","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv:1612.03928"},{"key":"ref5","article-title":"Contrastive representation distillation","author":"Tian","year":"2019","journal-title":"arXiv:1910.10699"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01328"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00067"},{"key":"ref9","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref11","first-page":"1","article-title":"Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20240"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref15","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref17","article-title":"Policy distillation","author":"Rusu","year":"2015","journal-title":"arXiv:1511.06295"},{"key":"ref18","article-title":"N2N learning: Network to network compression via policy gradient reinforcement learning","author":"Ashok","year":"2017","journal-title":"arXiv:1709.06030"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00360"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/428"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/573"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01545"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3461353.3461367"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01253"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref29","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref30","article-title":"ViDT: An efficient and effective fully transformer-based object detector","author":"Song","year":"2021","journal-title":"arXiv:2110.03921"},{"key":"ref31","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref32","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref34","article-title":"UP-DETR: Unsupervised pre-training for object detection with transformers","author":"Dai","year":"2020","journal-title":"arXiv:2011.09094"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref38","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref40","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020","journal-title":"arXiv:2012.12877"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref42","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021","journal-title":"arXiv:2103.11886"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref49","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"arXiv:1506.01497"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867198"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974745"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3149780"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.255"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref57","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref58","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00298"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_13"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.09.031"},{"key":"ref62","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020","journal-title":"arXiv:2006.09882"},{"key":"ref63","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref64","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref65","volume-title":"Caltech 101","author":"Li","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1994.413520"},{"key":"ref67","volume-title":"Blur is an Ensemble: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness","author":"Park","year":"2022"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10091778.pdf?arnumber=10091778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T21:05:38Z","timestamp":1709240738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3263105","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}