{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:02:48Z","timestamp":1777568568168,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726903","type":"print"},{"value":"9783031726910","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72691-0_14","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:05:53Z","timestamp":1730570753000},"page":"238-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["AugDETR: Improving Multi-scale Learning for\u00a0Detection Transformer"],"prefix":"10.1007","author":[{"given":"Jinpeng","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"14_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":"14_CR2","unstructured":"Cai, Z., Liu, S., Wang, G., Ge, Z., Zhang, X., Huang, D.: Align-detr: improving detr with simple iou-aware bce loss. arXiv preprint arXiv:2304.07527 (2023)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Cao, X., Yuan, P., Feng, B., Niu, K.: Cf-detr: coarse-to-fine transformers for end-to-end object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 185\u2013193 (2022)","DOI":"10.1609\/aaai.v36i1.19893"},{"key":"14_CR4","doi-asserted-by":"publisher","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.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Q., Chen, X., Zeng, G., Wang, J.: Group detr: fast training convergence with decoupled one-to-many label assignment. arXiv preprint arXiv:2207.13085 (2022)","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Yang, J., Zhang, P., Yuan, L., Zhang, L.: Dynamic detr: end-to-end object detection with dynamic attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2988\u20132997 (2021)","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31 $$\\times $$ 31: revisiting large kernel design in cnns. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11963\u201311975 (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Dong, J., Huang, Y., Zhang, S., Chen, S., Zheng, N.: Construct effective geometry aware feature pyramid network for multi-scale object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 534\u2013541 (2022)","DOI":"10.1609\/aaai.v36i1.19932"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"14_CR10","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\/CVF International Conference on Computer Vision, pp. 3621\u20133630 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., Fan, B., Zhang, Q., Xiang, S., Pan, C.: Augfpn: improving multi-scale feature learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12595\u201312604 (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"He, Y., Zhu, C., Wang, J., Savvides, M., Zhang, X.: Bounding box regression with uncertainty for accurate object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2888\u20132897 (2019)","DOI":"10.1109\/CVPR.2019.00300"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Jia, D., et al.: Detrs with hybrid matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19702\u201319712 (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Kim, S.W., Kook, H.K., Sun, J.Y., Kang, M.C., Ko, S.J.: Parallel feature pyramid network for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 234\u2013250 (2018)","DOI":"10.1007\/978-3-030-01228-1_15"},{"key":"14_CR16","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","volume":"29","author":"T Kong","year":"2020","unstructured":"Kong, T., Sun, F., Liu, H., Jiang, Y., Li, L., Shi, J.: Foveabox: beyound anchor-based object detection. IEEE Trans. Image Process. 29, 7389\u20137398 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Dn-detr: accelerate detr training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"14_CR19","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural Inf. Process. Syst. 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"14_CR20","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":"14_CR21","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":"14_CR22","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-Y Lin","year":"2014","unstructured":"Lin, T.-Y., 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":"14_CR23","doi-asserted-by":"crossref","unstructured":"Lin, Y., Yuan, Y., Zhang, Z., Li, C., Zheng, N., Hu, H.: Detr does not need multi-scale or locality design. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6545\u20136554 (2023)","DOI":"10.1109\/ICCV51070.2023.00602"},{"key":"14_CR24","unstructured":"Liu, S., et al.: Dab-detr: dynamic anchor boxes are better queries for detr. In: International Conference on Learning Representations (2021)"},{"key":"14_CR25","unstructured":"Liu, S., et\u00a0al.: Detection transformer with stable matching. arXiv preprint arXiv:2304.04742 (2023)"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"14_CR27","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":"14_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional detr for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Nguyen, D.K., Ju, J., Booij, O., Oswald, M.R., Snoek, C.G.: Boxer: box-attention for 2d and 3d transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4773\u20134782 (2022)","DOI":"10.1109\/CVPR52688.2022.00473"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra r-cnn: towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 821\u2013830 (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"14_CR32","unstructured":"Pu, Y., et al.: Rank-detr for high quality object detection. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Qiao, S., Chen, L.C., Yuille, A.: Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10213\u201310224 (2021)","DOI":"10.1109\/CVPR46437.2021.01008"},{"issue":"6","key":"14_CR34","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":"14_CR35","unstructured":"Roh, B., Shin, J., Shin, W., Kim, S.: Sparse detr: efficient end-to-end object detection with learnable sparsity. In: International Conference on Learning Representations (2021)"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"14_CR37","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":"14_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor detr: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: Simmim: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, G., Luo, Z., Tian, Z., Zhang, J., Zhang, X., Lu, S.: Towards efficient use of multi-scale features in transformer-based object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6206\u20136216 (2023)","DOI":"10.1109\/CVPR52729.2023.00601"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, G., Luo, Z., Yu, Y., Cui, K., Lu, S.: Accelerating detr convergence via semantic-aligned matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 949\u2013958 (2022)","DOI":"10.1109\/CVPR52688.2022.00102"},{"key":"14_CR42","unstructured":"Zhang, H., et al.: Dino: detr with improved denoising anchor boxes for end-to-end object detection. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: Varifocalnet: an iou-aware dense object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"14_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-030-58555-6_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic R-CNN: towards high quality object detection via dynamic training. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 260\u2013275. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_16"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Dense distinct query for end-to-end object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7329\u20137338 (2023)","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., Chen, X., Wang, Y.: Less is more: focus attention for efficient detr. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6674\u20136683 (2023)","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"14_CR47","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhuo, J., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 850\u2013859 (2019)","DOI":"10.1109\/CVPR.2019.00094"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 840\u2013849 (2019)","DOI":"10.1109\/CVPR.2019.00093"},{"key":"14_CR50","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: Detrs with collaborative hybrid assignments training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72691-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:07:27Z","timestamp":1730570847000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72691-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726903","9783031726910"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72691-0_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}