{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:02:13Z","timestamp":1786978933232,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":50,"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_6","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T12:21:52Z","timestamp":1667650912000},"page":"88-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["Towards Data-Efficient Detection Transformers"],"prefix":"10.1007","author":[{"given":"Wen","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongliang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y.H., Yu, H., Wu, J.: Training vision transformers with only 2040 images. arXiv preprint arXiv:2201.10728 (2022)","DOI":"10.1007\/978-3-031-19806-9_13"},{"key":"6_CR3","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 \u2013 ECCV 2020","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":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, J., Tao, D.: Recurrent glimpse-based decoder for detection with transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5260\u20135269 (2022)","DOI":"10.1109\/CVPR52688.2022.00519"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Xie, L., Niu, J., Liu, X., Wei, L., Tian, Q.: Visformer: the vision-friendly transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 589\u2013598 (2021)","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"6_CR6","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., Shen, C.: Twins: Revisiting the design of spatial attention in vision transformers. In: 34th Proceedings of the International Conference on Advances in Neural Information Processing Systems (2021)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: UP-DETR: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"6_CR9","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.ac In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Fang, J., Xie, L., Wang, X., Zhang, X., Liu, W., Tian, Q.: Msg-transformer: exchanging local spatial information by manipulating messenger tokens. arXiv preprint arXiv:2105.15168 (2021)","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"6_CR12","unstructured":"Fang, Y., et al.: You only look at one sequence: rethinking transformer in vision through object detection. arXiv preprint arXiv:2106.00666 (2021)"},{"issue":"9","key":"6_CR13","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2009","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of DETR with spatially modulated co-attention. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Ge, Z., Liu, S., Li, Z., Yoshie, O., Sun, J.: OTA: optimal transport assignment for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 303\u2013312 (2021)","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semaantic segmentation. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"6_CR17","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. In: 34th Proceedings of the Conference on Advances in Neural Information Processing Systems (2021)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR20","unstructured":"Jia, X., De Brabandere, B., Tuytelaars, T., Gool, L.V.: Dynamic filter networks. In: 29th Proceedings of the Conference on Advances in Neural Information Processing Systems (2016)"},{"key":"6_CR21","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics, pp. 562\u2013570. PMLR (2015)"},{"key":"6_CR22","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"6_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Lin","year":"2014","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Liu, F., Wei, H., Zhao, W., Li, G., Peng, J., Li, Z.: WB-DETR: transformer-based detector without backbone. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2979\u20132987 (2021)","DOI":"10.1109\/ICCV48922.2021.00297"},{"key":"6_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"6_CR27","unstructured":"Liu, Y., Sangineto, E., Bi, W., Sebe, N., Lepri, B., Nadai, M.: Efficient training of visual transformers with small datasets. In: 34th Proceedings of the Conference on Advances in Neural Information Processing Systems (2021)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"6_CR31","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Shen, Y., et al.: Parallel instance query network for named entity recognition. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (2022). arxiv.org\/abs\/2203.10545","DOI":"10.18653\/v1\/2022.acl-long.67"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse r-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"6_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-58452-8_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 282\u2013298. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_17"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"6_CR36","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"6_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Conference on Neural Information Processing Systems (2017)"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2965\u20132974 (2019)","DOI":"10.1109\/CVPR.2019.00308"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Wang, T., Yuan, L., Chen, Y., Feng, J., Yan, S.: PNP-DETR: towards efficient visual analysis with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"6_CR40","unstructured":"Wang, W., Cao, Y., Zhang, J., Tao, D.: FP-DETR: detection transformer advanced by fully pre-training. In: International Conference on Learning Representations (2022). \u2019openreview.net\/forum?id=yjMQuLLcGWK"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"6_CR42","unstructured":"Xu, Y., Zhang, Q., Zhang, J., Tao, D.: Vitae: vision transformer advanced by exploring intrinsic inductive bias. In: 34th Proceedings of the Conference on Advances in Neural Information Processing Systems (2021)"},{"key":"6_CR43","unstructured":"Yang, T., Zhang, X., Li, Z., Zhang, W., Sun, J.: Metaanchor: learning to detect objects with customized anchaors. In: 31st Proceedings of the Conference on Advances in Neural Information Processing Systems (2018)"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: Polyphonicformer: unified query learning for depth-aware video panoptic segmentation. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19812-0_34"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token VIT: training vision transformers from scratch on ImageNet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Xu, Y., Zhang, J., Tao, D.: Vitaev2: vision transformer advanced by exploring inductive bias for image recognition and beyond. arXiv preprint aarXiv:2202.10108 (2022)","DOI":"10.1007\/s11263-022-01739-w"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference ON Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"6_CR48","unstructured":"Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: Freeanchor: Learning to match anchors for visual object detection. In: 32nd Proceedings of the Conference on Advances in Neural Information Processing Systems (2019)"},{"key":"6_CR49","unstructured":"Zhu, B., et al.: Autoassign: differentiable label assignment for dense object detection. arXiv preprint arXiv:2007.03496 (2020)"},{"key":"6_CR50","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning and Representations (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_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T01:51:39Z","timestamp":1678499499000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_6","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)"}}]}}