{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:52:14Z","timestamp":1774720334949,"version":"3.50.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732539","type":"print"},{"value":"9783031732546","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"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\/978-3-031-73254-6_1","type":"book-chapter","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T07:24:25Z","timestamp":1732692265000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MutDet: Mutually Optimizing Pre-training for\u00a0Remote Sensing Object Detection"],"prefix":"10.1007","author":[{"given":"Ziyue","family":"Huang","sequence":"first","affiliation":[]},{"given":"Yongchao","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Qingjie","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bar, A., et al.: DETReg: unsupervised pretraining with region priors for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14605\u201314615 (2022)","DOI":"10.1109\/CVPR52688.2022.01420"},{"key":"1_CR2","unstructured":"Bouniot, Q., Audigier, R., Loesch, A., Habrard, A.: Proposal-contrastive pretraining for object detection from fewer data. In: International Conference on Learning Representations (2023)"},{"key":"1_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":"1_CR4","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chang, J., Wang, S., Xu, H.M., Chen, Z., Yang, C., Zhao, F.: DETRDistill: a universal knowledge distillation framework for DETR-families. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6898\u20136908 (2023)","DOI":"10.1109\/ICCV51070.2023.00635"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Chen, D., Mei, J.P., Zhang, H., Wang, C., Feng, Y., Chen, C.: Knowledge distillation with the reused teacher classifier. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11933\u201311942 (2022)","DOI":"10.1109\/CVPR52688.2022.01163"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Q., et al.: Group DETR: fast DETR training with group-wise one-to-many assignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6633\u20136642 (2023)","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision, pp. 9620\u20139629 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"1_CR9","first-page":"1","volume":"60","author":"G Cheng","year":"2022","unstructured":"Cheng, G., et al.: Anchor-free oriented proposal generator for object detection. IEEE Trans. Geosci. Remote Sens. 60, 1\u201311 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"5","key":"1_CR10","doi-asserted-by":"publisher","first-page":"2342","DOI":"10.1109\/TCSVT.2022.3222906","volume":"33","author":"L Dai","year":"2023","unstructured":"Dai, L., Liu, H., Tang, H., Wu, Z., Song, P.: AO2-DETR: arbitrary-oriented object detection transformer. IEEE Trans. Circuits Syst. Video Technol. 33(5), 2342\u20132356 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1_CR11","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Long, Y., Xia, G.S., Lu, Q.: Learning ROI transformer for oriented object detection in aerial images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2849\u20132858 (2019)","DOI":"10.1109\/CVPR.2019.00296"},{"key":"1_CR13","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Han, J., Ding, J., Xue, N., Xia, G.S.: ReDet: a rotation-equivariant detector for aerial object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2786\u20132795 (2021)","DOI":"10.1109\/CVPR46437.2021.00281"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Z., et al.: EMO2-DETR: efficient-matching oriented object detection with transformers. IEEE Trans. Geosci. Remote Sens. (2023)","DOI":"10.1109\/TGRS.2023.3300154"},{"issue":"4","key":"1_CR16","first-page":"4071","volume":"45","author":"G Huang","year":"2022","unstructured":"Huang, G., Laradji, I., Vazquez, D., Lacoste-Julien, S., Rodriguez, P.: A survey of self-supervised and few-shot object detection. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4071\u20134089 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Huang, G., et al.: Siamese DETR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15722\u201315731 (2023)","DOI":"10.1109\/CVPR52729.2023.01509"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"1_CR19","unstructured":"Lee, H., Song, M., Koo, J., Seo, J.: RHINO: rotated DETR with dynamic denoising via Hungarian matching for oriented object detection. arXiv preprint arXiv:2305.07598 (2023)"},{"key":"1_CR20","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","volume":"159","author":"K Li","year":"2020","unstructured":"Li, K., Wan, G., Cheng, G., Meng, L., Han, J.: Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J. Photogramm. Remote. Sens. 159, 296\u2013307 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: AlignDet: aligning pre-training and fine-tuning in object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6866\u20136876 (2023)","DOI":"10.1109\/ICCV51070.2023.00632"},{"key":"1_CR22","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":"1_CR23","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":"1_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"1_CR25","unstructured":"Ma, T., et al.: Oriented object detection with transformer. arXiv preprint arXiv:2106.03146 (2021)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1_CR27","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.isprsjprs.2021.12.004","volume":"184","author":"X Sun","year":"2022","unstructured":"Sun, X., et al.: FAIR1M: a benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery. ISPRS J. Photogramm. Remote. Sens. 184, 116\u2013130 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1_CR28","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vision 104, 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vision"},{"key":"1_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, Y., Zheng, Z., Li, X., Cheng, M.M., Hou, Q.: CrossKD: cross-head knowledge distillation for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16520\u201316530 (2024)","DOI":"10.1109\/CVPR52733.2024.01563"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Revisiting the transferability of supervised pretraining: an MLP perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9183\u20139193 (2022)","DOI":"10.1109\/CVPR52688.2022.00897"},{"key":"1_CR32","first-page":"22682","volume":"34","author":"F Wei","year":"2021","unstructured":"Wei, F., Gao, Y., Wu, Z., Hu, H., Lin, S.: Aligning pretraining for detection via object-level contrastive learning. Adv. Neural. Inf. Process. Syst. 34, 22682\u201322694 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Xia, G.S., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3974\u20133983 (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented R-CNN for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3520\u20133529 (2021)","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"1_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-031-20077-9_8","volume-title":"Computer Vision \u2013 ECCV 2022","author":"C Yang","year":"2022","unstructured":"Yang, C., Ochal, M., Storkey, A., Crowley, E.J.: Prediction-guided distillation for dense object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 123\u2013138. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_8"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Yang, C., An, Z., Cai, L., Xu, Y.: Mutual contrastive learning for visual representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3045\u20133053 (2022)","DOI":"10.1609\/aaai.v36i3.20211"},{"issue":"5","key":"1_CR37","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1007\/s11263-022-01593-w","volume":"130","author":"X Yang","year":"2022","unstructured":"Yang, X., Yan, J.: On the arbitrary-oriented object detection: classification based approaches revisited. Int. J. Comput. Vision 130(5), 1340\u20131365 (2022)","journal-title":"Int. J. Comput. Vision"},{"issue":"4","key":"1_CR38","first-page":"4335","volume":"45","author":"X Yang","year":"2023","unstructured":"Yang, X., et al.: Detecting rotated objects as gaussian distributions and its 3-D generalization. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4335\u20134354 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR39","unstructured":"Yang, X., et al.: The KFIoU loss for rotated object detection. arXiv preprint arXiv:2201.12558 (2022)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Yu, Y., Da, F.: Phase-shifting coder: predicting accurate orientation in oriented object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13354\u201313363 (2023)","DOI":"10.1109\/CVPR52729.2023.01283"},{"key":"1_CR41","first-page":"1","volume":"62","author":"Y Zeng","year":"2024","unstructured":"Zeng, Y., Chen, Y., Yang, X., Li, Q., Yan, J.: ARS-DETR: aspect ratio-sensitive detection transformer for aerial oriented object detection. IEEE Trans. Geosci. Remote Sens. 62, 1\u201315 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1_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 (2023)"},{"issue":"8","key":"1_CR43","doi-asserted-by":"publisher","first-page":"5535","DOI":"10.1109\/TGRS.2019.2900302","volume":"57","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Yuan, Y., Feng, Y., Lu, X.: Hierarchical and robust convolutional neural network for very high-resolution remote sensing object detection. IEEE Trans. Geosci. Remote Sens. 57(8), 5535\u20135548 (2019)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Li, S.: ABFL: angular boundary discontinuity free loss for arbitrary oriented object detection in aerial images. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3368630"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Zheng, Z., et al.: Localization distillation for dense object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9407\u20139416 (2022)","DOI":"10.1109\/CVPR52688.2022.00919"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et\u00a0al.: MMRotate: a rotated object detection benchmark using pytorch. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 7331\u20137334 (2022)","DOI":"10.1145\/3503161.3548541"},{"key":"1_CR47","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 Representations (2021)"}],"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\/978-3-031-73254-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:03:52Z","timestamp":1732694632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73254-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"ISBN":["9783031732539","9783031732546"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73254-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"28 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"}}]}}