{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T19:42:19Z","timestamp":1776282139858,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China Project","award":["2022ZD0161100"],"award-info":[{"award-number":["2022ZD0161100"]}]},{"name":"Centre for Perceptual and Interactive Intelligence"},{"name":"Innovation and Technology Commission (ITC)'s InnoHK"},{"name":"General Research Fund of Hong Kong RGC Project","award":["14204021"],"award-info":[{"award-number":["14204021"]}]},{"name":"PI of CPII"},{"name":"InnoHK"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3319387","type":"journal-article","created":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T17:48:36Z","timestamp":1695750516000},"page":"15759-15771","source":"Crossref","is-referenced-by-count":12,"title":["Teach-DETR: Better Training DETR With Teachers"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9701-6487","authenticated-orcid":false,"given":"Linjiang","family":"Huang","sequence":"first","affiliation":[{"name":"Multimedia Laboratory, Centre for Perceptual and Interactive Intelligence (CPII), The Chinese University of Hong Kong, Hong Kong, China"}]},{"given":"Kaixin","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"given":"Guanglu","family":"Song","sequence":"additional","affiliation":[{"name":"Sensetime Research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Sensetime Research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2664-7975","authenticated-orcid":false,"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Multimedia Laboratory, Centre for Perceptual and Interactive Intelligence (CPII), The Chinese University of Hong Kong, Hong Kong, China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"DETRs with hybrid matching","author":"jia","year":"2022"},{"key":"ref35","article-title":"Knowledge distillation for detection transformer with consistent distillation points sampling","author":"wang","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"ref34","article-title":"DETR: Decoder distillation for detection transformer","author":"chen","year":"2022"},{"key":"ref15","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00357"},{"key":"ref30","first-page":"5213","article-title":"Distilling object detectors with feature richness","author":"zhixing","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"ref33","article-title":"DETRDistill: A universal knowledge distillation framework for DETR-families","author":"chang","year":"2022"},{"key":"ref10","article-title":"Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors","author":"zhang","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","article-title":"ViDT: An efficient and effective fully transformer-based object detector","author":"song","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref1","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"zhang","year":"2022"},{"key":"ref17","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref24","article-title":"Distilling object detectors with task adaptive regularization","author":"sun","year":"2020"},{"key":"ref23","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","author":"chen","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00919"},{"key":"ref20","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"liu","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref41","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","author":"fang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref22","article-title":"Group DETR: Fast training convergence with decoupled one-to-many label assignment","author":"chen","year":"2022"},{"key":"ref44","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref7","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref9","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref3","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref6","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref40","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10264211.pdf?arnumber=10264211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:33:06Z","timestamp":1743795186000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10264211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":44,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3319387","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":[[2023,12]]}}}