{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:46:56Z","timestamp":1771458416870,"version":"3.50.1"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836014"],"award-info":[{"award-number":["61836014"]}],"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":["U21B2042"],"award-info":[{"award-number":["U21B2042"]}],"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":["62072457"],"award-info":[{"award-number":["62072457"]}],"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":["62006231"],"award-info":[{"award-number":["62006231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3276392","type":"journal-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T19:45:39Z","timestamp":1684266339000},"page":"11856-11868","source":"Crossref","is-referenced-by-count":10,"title":["GAIA-Universe: Everything is Super-Netify"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5276-0114","authenticated-orcid":false,"given":"Junran","family":"Peng","sequence":"first","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8469-3945","authenticated-orcid":false,"given":"Qing","family":"Chang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9275-9839","authenticated-orcid":false,"given":"Haoran","family":"Yin","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6445-4306","authenticated-orcid":false,"given":"Xingyuan","family":"Bu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5802-7335","authenticated-orcid":false,"given":"Jiajun","family":"Sun","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Inc, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6337-5748","authenticated-orcid":false,"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Inc, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Inc, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]}],"member":"263","reference":[{"key":"ref57","first-page":"1","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","year":"2020"},{"key":"ref59","first-page":"1","article-title":"Designing neural network architectures using reinforcement learning","author":"baker","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00961"},{"key":"ref52","first-page":"2543","article-title":"ReSSL: Relational self-supervised learning with weak augmentation","author":"zheng","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref54","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","author":"rebuffi","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref51","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.692"},{"key":"ref48","article-title":"Pedestrian detection: The elephant in the room","author":"hasan","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00395"},{"key":"ref42","article-title":"Billion-scale semi-supervised learning for image classification","author":"yalniz","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref43","article-title":"An analysis of pre-training on object detection","author":"li","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00525"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref7","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019"},{"key":"ref9","first-page":"1","article-title":"Once for all: Train one network and specialize it for efficient deployment","author":"cai","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585893"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref100","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"ge","year":"2021"},{"key":"ref101","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00034"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","article-title":"Florence: A new foundation model for computer vision","author":"yuan","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref23","article-title":"The open images dataset V4: Unified image classification, object detection, and visual relationship detection at scale","author":"kuznetsova","year":"2018"},{"key":"ref26","article-title":"Masked-attention mask transformer for universal image segmentation","author":"cheng","year":"2021"},{"key":"ref25","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"cheng","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref21","first-page":"7281","article-title":"Towards universal object detection by domain attention","author":"ang","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref27","first-page":"833","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref13","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/30.1-2.81"},{"key":"ref99","article-title":"Augment your batch: Better training with larger batches","author":"hoffer","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref18","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref93","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref92","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"zhai","year":"2019"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00190"},{"key":"ref86","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref87","article-title":"The PASCAL visual object classes challenge 2012 (VOC2012) results","author":"everingham","year":"2012"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_25"},{"key":"ref81","article-title":"Rethinking ImageNet pre-training","author":"he","year":"2018"},{"key":"ref84","article-title":"Stochastic gradient methods with layer-wise adaptive moments for training of deep networks","author":"ginsburg","year":"2019"},{"key":"ref83","article-title":"BDD100K: A large-scale diverse driving video database","volume":"511","author":"seita","year":"2018","journal-title":"Berkeley Artif Intell Res Blog Version"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref75","article-title":"Detectron2","author":"wu","year":"2019"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.474"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref72","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_11"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref66","first-page":"45","article-title":"Software framework for topic modelling with large corpora","author":"?eh??ek","year":"2010","journal-title":"Proc LREC Workshop"},{"key":"ref65","article-title":"Searching for efficient multi-stage vision transformers","author":"liao","year":"2021","journal-title":"arXiv 2109 00642"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11709"},{"key":"ref62","article-title":"Vision transformer architecture search","author":"su","year":"2021"},{"key":"ref61","first-page":"1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2019","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10125046.pdf?arnumber=10125046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:13:02Z","timestamp":1717693982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10125046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":106,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3276392","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":[[2023,10]]}}}