{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T17:39:56Z","timestamp":1793727596965,"version":"4.6.1"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20077-9_17","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T12:21:52Z","timestamp":1667650912000},"page":"280-296","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":775,"title":["Exploring Plain Vision Transformer Backbones for\u00a0Object Detection"],"prefix":"10.1007","author":[{"given":"Yanghao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanzi","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Girshick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiming","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"17_CR1","unstructured":"Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image Transformers. arXiv:2106.08254 (2021)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS - improving object detection with one line of code. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.593"},{"issue":"5","key":"17_CR3","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and instance segmentation. TPAMI 43(5), 1483\u20131498 (2019)","journal-title":"TPAMI"},{"key":"17_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Hybrid task cascade for instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., Sun, J.: You only look one-level feature. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"17_CR7","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv:1604.06174 (2016)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: A simple single-scale vision transformer for object localization and instance segmentation. arXiv:2112.09747 (2021)","DOI":"10.1007\/978-3-031-20080-9_41"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: Dynamic head: unifying object detection heads with attentions. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional Transformers for language understanding. In: NAACL (2019)"},{"key":"17_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 x 16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"17_CR14","unstructured":"El-Nouby, A., et al.: XCiT: cross-covariance image transformers. In: NeurIPS (2021)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale Vision Transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"17_CR16","unstructured":"Fu, W., Nie, C., Sun, T., Liu, J., Zhang, T., Liu, Y.: LVIS challenge track technical report 1st place solution: distribution balanced and boundary refinement for large vocabulary instance segmentation. arXiv:2111.02668 (2021)"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"17_CR20","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour. arXiv:1706.02677 (2017)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"17_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"issue":"4","key":"17_CR29","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C.Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., Feichtenhofer, C.: MViTv2: improved multiscale Vision Transformers for classification and detection. arXiv:2112.01526 (2021)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"17_CR32","unstructured":"Li, Y., Xie, S., Chen, X., Dollar, P., He, K., Girshick, R.: Benchmarking detection transfer learning with Vision Transformers. arXiv:2111.11429 (2021)"},{"key":"17_CR33","unstructured":"Liang, T., et al.: CBNetV2: a composite backbone network architecture for object detection. arXiv:2107.00420 (2021)"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer V2: scaling up capacity and resolution. arXiv:2111.09883 (2021)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"17_CR40","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"17_CR41","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"17_CR42","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"17_CR43","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. In: JMLR (2020)"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"17_CR45","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"17_CR46","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"17_CR49","unstructured":"Tolstikhin, I., et al.: MLP-mixer: an all-MLP architecture for vision. In: NeurIPS (2021)"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Touvron, H., et al.: ResMLP: feedforward networks for image classification with data-efficient training. arXiv:2105.03404 (2021)","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"17_CR51","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid Vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. arXiv:2106.04560 (2021)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"17_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. arXiv:2201.02605 (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"17_CR55","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Probabilistic two-stage detection. arXiv preprint arXiv:2103.07461 (2021)"},{"key":"17_CR56","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20077-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T19:12:14Z","timestamp":1667848334000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"6 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}