{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:45:59Z","timestamp":1785653159223,"version":"3.56.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31666-0_10","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:44Z","timestamp":1785649664000},"page":"143-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Few-Shot Adaptive Open-Set Object Detection with\u00a0Personalized Scene Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5172-5798","authenticated-orcid":false,"given":"Yuzuru","family":"Nakamura","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4630-3464","authenticated-orcid":false,"given":"Yasunori","family":"Ishii","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2631-9856","authenticated-orcid":false,"given":"Takayoshi","family":"Yamashita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Benigmim, Y., Roy, S., Essid, S., Kalogeiton, V., Lathuili\u00e8re, S.: One-shot unsupervised domain adaptation with personalized diffusion models. In: Proceedings of CVPRW, pp. 698\u2013708 (2023)","DOI":"10.1109\/CVPRW59228.2023.00077"},{"key":"10_CR2","unstructured":"Chen, M., et al.: Learning domain adaptive object detection with probabilistic teacher. In: Proceedings of ICML, vol.\u00a0162, pp. 3040\u20133055 (2022)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster R-CNN for object detection in the wild. In: Proceedings of CVPR, pp. 3339\u20133348 (2018)","DOI":"10.1109\/CVPR.2018.00352"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: Cogview2: faster and better text-to-image generation via hierarchical transformers. In: Proceedings of NeurIPS, vol. 35, pp. 16890\u201316902 (2022)","DOI":"10.52202\/068431-1229"},{"key":"10_CR6","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: Proceedings of ICLR (2023)"},{"key":"10_CR7","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: Proceedings of ICML, pp. 1180\u20131189 (2015)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Gao, Y., Lin, K.Y., Yan, J., Wang, Y., Zheng, W.S.: ASYFOD: an asymmetric adaptation paradigm for few-shot domain adaptive object detection. In: Proceedings of CVPR, pp. 3261\u20133271 (2023)","DOI":"10.1109\/CVPR52729.2023.00318"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Gao, Y., Yang, L., Huang, Y., Xie, S., Li, S., Zheng, W.S.: ACROFOD: an adaptive method for cross-domain few-shot object detection. In: Proceedings of ECCV, pp. 673\u2013690 (2022)","DOI":"10.1007\/978-3-031-19827-4_39"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: Proceedings of CVPR, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR12","unstructured":"Jocher, G., et\u00a0al.: ultralytics\/yolov5: v3.0 - third release. Tech. rep., Zenodo (2020)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Johnson-Roberson, M., Barto, C., Mehta, R., Sridhar, S.N., Rosaen, K., Vasudevan, R.: Driving in the matrix: can virtual worlds replace human-generated annotations for real world tasks? In: Proceedings of ICRA, pp. 746\u2013753 (2017)","DOI":"10.1109\/ICRA.2017.7989092"},{"key":"10_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Proceedings of ICLR (2014)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Li, W., Guo, X., Yuan, Y.: Novel scenes & classes: towards adaptive open-set object detection. In: Proceedings of ICCV, pp. 15780\u201315790 (2023)","DOI":"10.1109\/ICCV51070.2023.01446"},{"key":"10_CR16","unstructured":"Li, Y.J., et al.: Cross-domain adaptive teacher for object detection. In: Proceedings of CVPR, pp. 7581\u20137590 (2022)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: Proceedings of ECCV, pp. 38\u201355 (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"10_CR18","unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: Proceedings of ICML, vol. 162, pp. 16784\u201316804 (2022)"},{"key":"10_CR19","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: Proceedings of ICLR (2024)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Ram, S., Neiman, T., Feng, Q., Stuart, A.M., Tran, S., A\u00a0Chilimbi, T.: DreamBlend: advancing personalized fine-tuning of text-to-image diffusion models. In: Proceedings of WACV, pp. 3614\u20133623 (2025)","DOI":"10.1109\/WACV61041.2025.00356"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Ramamonjison, R., Banitalebi-Dehkordi, A., Kang, X., Bai, X., Zhang, Y.: Simrod: a simple adaptation method for robust object detection. In: Proceedings of ICCV, pp. 3570\u20133579 (2021)","DOI":"10.1109\/ICCV48922.2021.00355"},{"key":"10_CR22","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"10_CR23","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of NeurIPS, vol. 28 (2015)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of CVPR, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Proceedings of NeurIPS, vol. 35, pp. 36479\u201336494 (2022)","DOI":"10.52202\/068431-2643"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: Proceedings of CVPR, pp. 6956\u20136965 (2019)","DOI":"10.1109\/CVPR.2019.00712"},{"key":"10_CR28","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. IJCV 126, 973\u2013992 (2018)","journal-title":"IJCV"},{"key":"10_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR (2015)"},{"key":"10_CR30","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Proceedings of NeurIPS, vol. 30 (2017)"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, X., Yuan, L., Feng, J.: Few-shot adaptive faster R-CNN. In: Proceedings of CVPR, pp. 7173\u20137182 (2019)","DOI":"10.1109\/CVPR.2019.00734"},{"key":"10_CR32","unstructured":"Wang, X., Huang, T., Gonzalez, J., Darrell, T., Yu, F.: Frustratingly simple few-shot object detection. In: Proceedings of ICML, vol. 119, pp. 9919\u20139928 (2020)"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of CVPR, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Zhong, C., Wang, J., Feng, C., Zhang, Y., Sun, J., Yokota, Y.: Pica: point-wise instance and centroid alignment based few-shot domain adaptive object detection with loose annotations. In: Proceedings of WACV, pp. 2329\u20132338 (2022)","DOI":"10.1109\/WACV51458.2022.00047"},{"key":"10_CR35","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: Proceedings of the ICLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:46Z","timestamp":1785649666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}