{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:20:52Z","timestamp":1757542852197,"version":"3.41.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031916717","type":"print"},{"value":"9783031916724","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91672-4_15","type":"book-chapter","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:25:16Z","timestamp":1747754716000},"page":"236-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Task-Specific Adaptation of\u00a0Segmentation Foundation Model via\u00a0Prompt Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6425-549X","authenticated-orcid":false,"given":"Hyung-Il","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4493-9437","authenticated-orcid":false,"given":"Kimin","family":"Yun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8319-6437","authenticated-orcid":false,"given":"Jun-Seok","family":"Yun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4979-2649","authenticated-orcid":false,"given":"Yuseok","family":"Bae","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"15_CR1","unstructured":"Kaggle car license plate detection. https:\/\/www.kaggle.com\/datasets\/andrewmvd\/car-plate-detection. Accessed 7 Mar 2024"},{"key":"15_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Bai, Y., Chen, D., Li, Q., Shen, W., Wang, Y.: Bidirectional copy-paste for semi-supervised medical image segmentation. In: CVPR, pp. 11514\u201311524 (2023)","DOI":"10.1109\/CVPR52729.2023.01108"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: YOLACT: real-time instance segmentation. In: ICCV, pp. 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"15_CR5","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"15_CR6","unstructured":"Cao, Y., et al.: Segment any anomaly without training via hybrid prompt regularization. arXiv preprint arXiv:2305.10724 (2023)"},{"key":"15_CR7","unstructured":"Cen, J., et al.: Segment anything in 3D with NeRFs. In: NeurIPS (2023)"},{"key":"15_CR8","unstructured":"Chen, X., Wang, C., Ning, H., Li, S.: SAM-OCTA: Prompting segment-anything for octa image segmentation. arXiv preprint arXiv:2310.07183 (2023)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Tian, Z., Zhu, J., Li, C., Du, S.: C-CAM: causal cam for weakly supervised semantic segmentation on medical image. In: CVPR, pp. 11676\u201311685 (2022)","DOI":"10.1109\/CVPR52688.2022.01138"},{"key":"15_CR10","unstructured":"Cheng, Y., et al.: Segment and track anything. arXiv preprint arXiv:2305.06558 (2023)"},{"key":"15_CR11","unstructured":"Dong, B., Zeng, F., Wang, T., Zhang, X., Wei, Y.: SOLQ: segmenting objects by learning queries. In: NeurIPS, pp. 21898\u201321909 (2021)"},{"key":"15_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Instances as queries. In: ICCV, pp. 6910\u20136919 (2021)","DOI":"10.1109\/ICCV48922.2021.00683"},{"issue":"3","key":"15_CR14","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"15_CR16","unstructured":"Hu, E.J., et al.: LoRA: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"15_CR17","unstructured":"Hu, J., et al.: ISTR: End-to-end instance segmentation with transformers. arXiv preprint arXiv:2105.00637 (2021)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X.: Mask scoring R-CNN. In: CVPR, pp. 6409\u20136418 (2019)","DOI":"10.1109\/CVPR.2019.00657"},{"key":"15_CR19","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: ECCV, pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"15_CR21","unstructured":"Ke, L., et al.: Segment anything in high quality. In: NeurIPS (2023)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: CenterMask: real-time anchor-free instance segmentation. In: CVPR, pp. 13906\u201313915 (2020)","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: EMNLP, pp. 3045\u20133059 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15_CR28","unstructured":"Ling, H., Kreis, K., Li, D., Kim, S.W., Torralba, A., Fidler, S.: EditGAN: high-precision semantic image editing. In: NeurIPS, pp. 16331\u201316345 (2021)"},{"issue":"9","key":"15_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: P-Tuning V2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"issue":"1","key":"15_CR32","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15(1), 654 (2024)","journal-title":"Nat. Commun."},{"key":"15_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918","volume":"89","author":"MA Mazurowski","year":"2023","unstructured":"Mazurowski, M.A., Dong, H., Gu, H., Yang, J., Konz, N., Zhang, Y.: Segment anything model for medical image analysis: an experimental study. Med. Image Anal. 89, 102918 (2023)","journal-title":"Med. Image Anal."},{"key":"15_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"15_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Siam, M., Gamal, M., Abdel-Razek, M., Yogamani, S., Jagersand, M., Zhang, H.: A comparative study of real-time semantic segmentation for autonomous driving. In: CVPRW, pp. 587\u2013597 (2018)","DOI":"10.1109\/CVPRW.2018.00101"},{"key":"15_CR37","unstructured":"Tang, L., Xiao, H., Li, B.: Can SAM segment anything? When SAM meets camouflaged object detection. arXiv preprint arXiv:2304.04709 (2023)"},{"key":"15_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"15_CR39","unstructured":"Wang, D., Zhang, J., Du, B., Tao, D., Zhang, L.: Scaling-up remote sensing segmentation dataset with segment anything model. arXiv preprint arXiv:2305.02034 (2023)"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: SOLO: segmenting objects by locations. In: ECCV, pp. 649\u2013665 (2020)","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"15_CR41","unstructured":"Wu, J., et al.: Medical SAM adapter: Adapting segment anything model for medical image segmentation. arXiv preprint arXiv:2304.12620 (2023)"},{"key":"15_CR42","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., Zheng, F.: Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)"},{"key":"15_CR43","unstructured":"Yu, T., et al.: Inpaint anything: Segment anything meets image inpainting. arXiv preprint arXiv:2304.06790 (2023)"},{"key":"15_CR44","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.1109\/LSP.2020.3022289","volume":"27","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Yang, P., Wang, W., Hong, Y., Zhang, L.: Image editing via segmentation guided self-attention network. IEEE Sign. Process. Letters 27, 1605\u20131609 (2020)","journal-title":"IEEE Sign. Process. Letters"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhuang, X.: CycleMix: a holistic strategy for medical image segmentation from scribble supervision. In: CVPR, pp. 11656\u201311665 (2022)","DOI":"10.1109\/CVPR52688.2022.01136"},{"key":"15_CR46","unstructured":"Zhang, R., et al.: Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048 (2023)"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, S., Metaxas, D.: On the challenges and perspectives of foundation models for medical image analysis. arXiv preprint arXiv:2306.05705 (2023)","DOI":"10.1016\/j.media.2023.102996"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Yang, C., Zhu, X., Yin, X.C.: Arbitrary shape text detection via boundary transformer. IEEE TMM (2023)","DOI":"10.1109\/TMM.2023.3286657"},{"key":"15_CR49","unstructured":"Zhou, T., Zhang, Y., Zhou, Y., Wu, Y., Gong, C.: Can SAM segment polyps? arXiv preprint arXiv:2304.07583 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91672-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:25:42Z","timestamp":1747754742000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91672-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031916717","9783031916724"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91672-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}