{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:10:59Z","timestamp":1778083859607,"version":"3.51.4"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729720","type":"print"},{"value":"9783031729737","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-72973-7_18","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"304-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Cascade Prompt Learning for\u00a0Vision-Language Model Adaptation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3011-091X","authenticated-orcid":false,"given":"Ge","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9078-9110","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3309-1087","authenticated-orcid":false,"given":"Zheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9508-6999","authenticated-orcid":false,"given":"Zhaowei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5586-340X","authenticated-orcid":false,"given":"Jiajun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4996-7365","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"18_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"18_CR2","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. ArXiv (2018)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"18_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. ArXiv (2020)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Fang, Z., Wang, J., Hu, X., Wang, L., Yang, Y., Liu, Z.: Compressing visual-linguistic model via knowledge distillation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00146"},{"key":"18_CR9","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: CVPR Workshops (2004)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. In: IJCV (2023)","DOI":"10.1007\/s11263-023-01891-x"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. ArXiv (2020)","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"18_CR12","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. ArXiv (2021)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J-STARS 12(7), 2217\u20132226 (2019)","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"18_CR17","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. ArXiv (2015)"},{"key":"18_CR18","unstructured":"Huang, T., Chu, J., Wei, F.: Unsupervised prompt learning for vision-language models. ArXiv (2022)"},{"key":"18_CR19","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"18_CR21","unstructured":"Jiao, S., Wei, Y., Wang, Y., Zhao, Y., Shi, H.: Learning mask-aware clip representations for zero-shot segmentation. ArXiv (2023)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: TinyBERT: distilling BERT for natural language understanding. ArXiv (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"18_CR23","unstructured":"Kahana, J., Cohen, N., Hoshen, Y.: Improving zero-shot models with label distribution priors. ArXiv (2022)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: MaPLe: multi-modal prompt learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., Khan, F.S.: Self-regulating prompts: Foundational model adaptation without forgetting. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: CVPR Workshops (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"18_CR27","unstructured":"Laroudie, C., Bursuc, A., Ha, M.L., Franchi, G.: Improving clip robustness with knowledge distillation and self-training. ArXiv (2023)"},{"key":"18_CR28","unstructured":"Lee, D.H., et\u00a0al.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: ICML Workshop (2013)"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. ArXiv (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. ArXiv (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: PromptKD: unsupervised prompt distillation for vision-language models. In: CVPR, pp. 26617\u201326626 (2024)","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Curriculum temperature for knowledge distillation. In: AAAI. vol.\u00a037, pp. 1504\u20131512 (2023)","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Li, Z., Ye, J., Song, M., Huang, Y., Pan, Z.: Online knowledge distillation for efficient pose estimation. In: ICCV, pp. 11740\u201311750 (2021)","DOI":"10.1109\/ICCV48922.2021.01153"},{"key":"18_CR34","doi-asserted-by":"crossref","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)","DOI":"10.1145\/3560815"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: P-tuning: prompt tuning can be comparable to fine-tuning across scales and tasks. In: ACL (2022)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, X., Nevatia, R.: Efficient feature distillation for zero-shot detection. ArXiv (2023)","DOI":"10.1109\/WACV57701.2024.00094"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, J., Zhang, Y., Liu, Y., Tian, X.: Prompt distribution learning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"18_CR39","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. ArXiv (2013)"},{"key":"18_CR40","unstructured":"Menghini, C., Delworth, A., Bach, S.H.: Enhancing clip with clip: exploring pseudolabeling for limited-label prompt tuning. In: NeurIPS (2023)"},{"key":"18_CR41","unstructured":"Mirza, M.J., et al.: LaFTer: label-free tuning of zero-shot classifier using language and unlabeled image collections. In: NeurIPS (2023)"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGIP (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"18_CR43","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"18_CR44","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to ImageNet? In: ICML (2019)"},{"key":"18_CR45","unstructured":"Schick, T., Sch\u00fctze, H.: Few-shot text generation with pattern-exploiting training. ArXiv (2020)"},{"key":"18_CR46","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild. ArXiv (2012)"},{"key":"18_CR47","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)"},{"key":"18_CR48","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: NeurIPS (2019)"},{"key":"18_CR49","unstructured":"Wang, Z., et\u00a0al.: Multimodal adaptive distillation for leveraging unimodal encoders for vision-language tasks. ArXiv (2022)"},{"key":"18_CR50","unstructured":"Wang, Z., et al.: CLIP-TD: Clip targeted distillation for vision-language tasks. ArXiv (2022)"},{"key":"18_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Z., et\u00a0al.: DualPrompt: complementary prompting for rehearsal-free continual learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Learning to prompt for continual learning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Wu, K., et\u00a0al.: TinyCLIP: clip distillation via affinity mimicking and weight inheritance. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Yang, C., An, Z., Cai, L., Xu, Y.: Mutual contrastive learning for visual representation learning. In: AAAI. vol.\u00a036, pp. 3045\u20133053 (2022)","DOI":"10.1609\/aaai.v36i3.20211"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: CLIP-KD: An empirical study of distilling clip models. ArXiv (2023)","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Yu, W., Liu, Y., Hua, W., Jiang, D., Ren, B., Bai, X.: Turning a clip model into a scene text detector. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"18_CR58","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Unified vision and language prompt learning. ArXiv (2022)"},{"key":"18_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wu, S., Gao, L., Shen, H., Song, J.: DePT: Decoupled prompt tuning. ArXiv (2023)","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"18_CR60","unstructured":"Zhang, R., et al.: Tip-adapter: Training-free clip-adapter for better vision-language modeling. ArXiv (2021)"},{"key":"18_CR61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3510781","volume":"62","author":"W Zhang","year":"2024","unstructured":"Zhang, W., Deng, W., Cui, Z., Liu, J., Jiao, L.: Object knowledge distillation for joint detection and tracking in satellite videos. IEEE Trans. Geosci. Remote Sens. 62, 1\u201313 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"18_CR62","unstructured":"Zhao, Z., Wallace, E., Feng, S., Klein, D., Singh, S.: Calibrate before use: improving few-shot performance of language models. In: ICML (2021)"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. IJCV (2022)","DOI":"10.1007\/s11263-022-01653-1"},{"key":"18_CR66","doi-asserted-by":"crossref","unstructured":"Zhu, B., Niu, Y., Han, Y., Wu, Y., Zhang, H.: Prompt-aligned gradient for prompt tuning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01435"}],"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\/978-3-031-72973-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T15:01:11Z","timestamp":1739631671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72973-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031729720","9783031729737"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72973-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}