{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:00:25Z","timestamp":1766268025754,"version":"3.41.0"},"reference-count":123,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2024.3411595","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T18:26:04Z","timestamp":1718130364000},"page":"5205-5222","source":"Crossref","is-referenced-by-count":0,"title":["UniDetector: Towards Universal Object Detection With Heterogeneous Supervision"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3701-8063","authenticated-orcid":false,"given":"Zhenyu","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6629-7228","authenticated-orcid":false,"given":"Yali","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5008-4720","authenticated-orcid":false,"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9525-0288","authenticated-orcid":false,"given":"Ser-Nam","family":"Lim","sequence":"additional","affiliation":[{"name":"Meta AI, Boston, MA, USA"}]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-2706","authenticated-orcid":false,"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7809-1932","authenticated-orcid":false,"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_27"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref13","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"article-title":"Objects as points","year":"2019","author":"Zhou","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2899569"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01171"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref37","first-page":"728","article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Minderer"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00524"},{"article-title":"Multi-dataset pretraining: A unified model for semantic segmentation","year":"2021","author":"Shi","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_11"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00746"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01097"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref49","first-page":"16797","article-title":"Comprehensive attention self-distillation for weakly-supervised object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"article-title":"Unbiased teacher for semi-supervised object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00315"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref53","first-page":"9534","article-title":"Combating noise: Semi-supervised learning by region uncertainty quantification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"article-title":"Weakly-and semi-supervised object detection with expectation-maximization algorithm","year":"2017","author":"Yan","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00936"},{"article-title":"WSSOD: A new pipeline for weakly-and semi-supervised object detection","year":"2021","author":"Fang","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00047"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00871"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00920"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_18"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00915"},{"key":"ref63","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref67","article-title":"Grounded segment anything"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3881-x"},{"article-title":"Segment anything in high quality","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ke","key":"ref71"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00096"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_16"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00441"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00553"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00937"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146922"},{"key":"ref78","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zoph"},{"article-title":"Yolov4: Optimal speed and accuracy of object detection","year":"2020","author":"Bochkovskiy","key":"ref79"},{"article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","key":"ref80"},{"article-title":"Decoupling representation and classifier for long-tailed recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kang","key":"ref81"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102430"},{"key":"ref86","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref87","first-page":"603","article-title":"On the statistical consistency of algorithms for binary classification under class imbalance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Menon"},{"article-title":"Long-tail learning via logit adjustment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon","key":"ref88"},{"key":"ref89","first-page":"2529","article-title":"On model calibration for long-tailed object detection and instance segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_42"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"article-title":"MMdetection: Open MMlab detection toolbox and benchmark","year":"2019","author":"Chen","key":"ref94"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00478"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00176"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01161"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref107"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","key":"ref108"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref112","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref115","first-page":"14074","article-title":"Open-vocabulary one-stage detection with hierarchical visual-language knowledge distillation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Ma"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"article-title":"Probabilistic two-stage detection","year":"2021","author":"Zhou","key":"ref117"},{"article-title":"Cascade RPN: Delving into high-quality region proposal network with adaptive convolution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vu","key":"ref118"},{"article-title":"Improved regularization of convolutional neural networks with cutout","year":"2017","author":"DeVries","key":"ref119"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_38"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548165"},{"article-title":"Vision-language models in remote sensing: Current progress and future trends","year":"2023","author":"Wen","key":"ref123"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10552883.pdf?arnumber=10552883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:14:31Z","timestamp":1749183271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10552883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":123,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3411595","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}