{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T08:08:33Z","timestamp":1774685313416,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665938","type":"print"},{"value":"9789819665945","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"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":[[2026]]},"DOI":"10.1007\/978-981-96-6594-5_22","type":"book-chapter","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T07:39:20Z","timestamp":1753083560000},"page":"299-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Based Domain Adaptive YOLO for Cross-Domain Object Detection"],"prefix":"10.1007","author":[{"given":"Zhiyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I","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.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I, pp. 213\u2013229. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Chen, C., Zheng, Z., Huang, Y., Ding, X., Yu, Y.: I3net: Implicit instance-invariant network for adapting one-stage object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12576\u201312585 (2021)","DOI":"10.1109\/CVPR46437.2021.01239"},{"key":"22_CR3","unstructured":"Chen, M., et\u00a0al.: Learning domain adaptive object detection with probabilistic teacher. arXiv preprint arXiv:2206.06293 (2022)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, W., Sakaridis, C., Dai, D., Van\u00a0Gool, L.: Domain adaptive faster R-CNN for object detection in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3339\u20133348 (2018)","DOI":"10.1109\/CVPR.2018.00352"},{"key":"22_CR5","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":"22_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Li, W., Chen, Y., Duan, L.: Unbiased mean teacher for cross-domain object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4091\u20134101 (2021)","DOI":"10.1109\/CVPR46437.2021.00408"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6568\u20136577 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"22_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"issue":"1","key":"22_CR9","first-page":"2030","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030\u20132096 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"He, M., et al.: Cross domain object detection by target-perceived dual branch distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9570\u20139580 (2022)","DOI":"10.1109\/CVPR52688.2022.00935"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"He, Z., Zhang, L.: Multi-adversarial faster-RCNN for unrestricted object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6668\u20136677 (2019)","DOI":"10.1109\/ICCV.2019.00677"},{"key":"22_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-030-58586-0_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z He","year":"2020","unstructured":"He, Z., Zhang, L.: Domain adaptive object detection via asymmetric tri-way faster-RCNN. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 309\u2013324. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_19"},{"issue":"8","key":"22_CR14","doi-asserted-by":"publisher","first-page":"5238","DOI":"10.1109\/TCSVT.2021.3138851","volume":"32","author":"Z He","year":"2021","unstructured":"He, Z., Zhang, L., Yang, Y., Gao, X.: Partial alignment for object detection in the wild. IEEE Trans. Circuits Syst. Video Technol. 32(8), 5238\u20135251 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Hnewa, M., Radha, H.: Multiscale domain adaptive yolo for cross-domain object detection. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3323\u20133327. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506039"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"22_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/978-3-030-58545-7_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C-C Hsu","year":"2020","unstructured":"Hsu, C.-C., Tsai, Y.-H., Lin, Y.-Y., Yang, M.-H.: Every pixel matters: center-aware feature alignment for domain adaptive object detector. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 733\u2013748. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_42"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Huang, S.W., Lin, C.T., Chen, S.P., Wu, Y.Y., Hsu, P.H., Lai, S.H.: Auggan: cross domain adaptation with GAN-based data augmentation. In: European Conference on Computer Vision, pp. 731\u2013744 (2018)","DOI":"10.1007\/978-3-030-01240-3_44"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Inoue, N., Furuta, R., Yamasaki, T., Aizawa, K.: Cross-domain weakly-supervised object detection through progressive domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5001\u20135009 (2018)","DOI":"10.1109\/CVPR.2018.00525"},{"key":"22_CR21","unstructured":"Jocher, G., et\u00a0al.: ultralytics\/yolov5: v6. 2-yolov5 classification models, apple m1, reproducibility, clearml and deci. ai integrations. Zenodo (2022)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Khodabandeh, M., Vahdat, A., Ranjbar, M., Macready, W.G.: A robust learning approach to domain adaptive object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (October 2019)","DOI":"10.1109\/ICCV.2019.00057"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: European Conference on Computer Vision, pp. 765\u2013781 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, X., Yuan, Y.: Sigma: Semantic-complete graph matching for domain adaptive object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5291\u20135300 (2022)","DOI":"10.1109\/CVPR52688.2022.00522"},{"key":"22_CR25","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":"22_CR26","unstructured":"Liu, Y., Shao, Z., Hoffmann, N.: Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561 (2021)"},{"key":"22_CR27","unstructured":"Liu, Y., Shao, Z., Teng, Y., Hoffmann, N.: Nam: Normalization-based attention module. arXiv preprint arXiv:2111.12419 (2021)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Luo, C., et al.: SAR-CDSS: A semi-supervised cross-domain object detection from optical to SAR domain. Remote Sensing 16(6) (2024)","DOI":"10.3390\/rs16060940"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Nguyen, D.K., Tseng, W.L., Shuai, H.H.: Domain-adaptive object detection via uncertainty-aware distribution alignment. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2499\u20132507 (2020)","DOI":"10.1145\/3394171.3413553"},{"issue":"2","key":"22_CR30","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","volume":"22","author":"SJ Pan","year":"2011","unstructured":"Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199\u2013210 (2011)","journal-title":"IEEE Trans. Neural Netw."},{"key":"22_CR31","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"},{"key":"22_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6956\u20136965 (2019)","DOI":"10.1109\/CVPR.2019.00712"},{"key":"22_CR34","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1007\/s11263-018-1072-8","volume":"126","author":"C Sakaridis","year":"2018","unstructured":"Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vision 126, 973\u2013992 (2018)","journal-title":"Int. J. Comput. Vision"},{"key":"22_CR35","unstructured":"Shen, Z., Maheshwari, H., Yao, W., Savvides, M.: SCL: Towards accurate domain adaptive object detection via gradient detach based stacked complementary losses. arXiv preprint arXiv:1911.02559 (2019)"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. p. 2058-2065 (2016)","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Xu, C.D., Zhao, X.R., Jin, X., Wei, X.S.: Exploring categorical regularization for domain adaptive object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11724\u201311733 (2020)","DOI":"10.1109\/CVPR42600.2020.01174"},{"key":"22_CR40","unstructured":"Yian, Z., et al.: DETRs beat YOLOs on real-time object detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u201310 (2024)"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Yin, X., Yu, Z., Fei, Z., Lv, W., Gao, X.: PE-YOLO: Pyramid enhancement network for dark object detection. In: International Conference on Artificial Neural Networks, pp. 163\u2013174. Springer (2023)","DOI":"10.1007\/978-3-031-44195-0_14"},{"key":"22_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103649","volume":"229","author":"H Zhou","year":"2023","unstructured":"Zhou, H., Jiang, F., Lu, H.: SSDA-YOLO: Semi-supervised domain adaptive yolo for cross-domain object detection. Comput. Vis. Image Underst. 229, 103649 (2023)","journal-title":"Comput. Vis. Image Underst."},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, W., Du, D., Zhang, L., Luo, T., Wu, Y.: Multi-granularity alignment domain adaptation for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9581\u20139590 (2022)","DOI":"10.1109\/CVPR52688.2022.00936"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6594-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T07:47:12Z","timestamp":1774684032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6594-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"ISBN":["9789819665938","9789819665945"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6594-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,22]]},"assertion":[{"value":"22 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}