{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:31:39Z","timestamp":1742985099778,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785018"},{"type":"electronic","value":"9789819785025"}],"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\/978-981-97-8502-5_8","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"104-117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Tuning of\u00a0CLIP in\u00a0Few-Shot Scenarios via\u00a0Supervised Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Jing","family":"Luo","sequence":"first","affiliation":[]},{"given":"Guangxing","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Hongmei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van\u00a0Gool, L.: Food-101\u2013mining discriminative components with random forests. In: ECCV, pp. 446\u2013461 (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"8_CR2","unstructured":"Chao, J., Yinfei, Y., Ye, X., et\u00a0al: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Chen, D., Zhang, J., Zheng, W.S., Wang, R.: Featwalk: Enhancing few-shot classification through local view leveraging. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 1019\u20131027 (2024)","DOI":"10.1609\/aaai.v38i2.27862"},{"key":"8_CR4","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao, Y., Zhang, K.: Plot: prompt learning with optimal transport for vision-language models (2022). arXiv:2210.01253"},{"key":"8_CR5","unstructured":"Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification (2019). arXiv:1904.04232"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Feng, L., Bichen, W., Xiaoliang, D., et\u00a0al: Open-vocabulary semantic segmentation with mask-adapted clip. In: CVPR, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"issue":"2","key":"8_CR9","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2023","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., Qiao, Y.: Clip-adapter: better vision-language models with feature adapters. IJCV 132(2), 581\u2013595 (2023)","journal-title":"IJCV"},{"issue":"7","key":"8_CR10","first-page":"2217","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. STARS 12(7), 2217\u20132226 (2019)","journal-title":"STARS"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., Mu, N., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: CVPR, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: CVPR, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Hongbo, S., Xiangteng, H., Jiahuan, Z., et\u00a0al: Fine-grained visual prompt learning of vision-language models for image recognition. In: ACM MM, pp. 5828\u20135836 (2023)","DOI":"10.1145\/3581783.3612403"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: ECCV, pp. 709\u2013727 (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"8_CR15","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., Teterwak, P., Wang, C., et al.: Supervised contrastive learning. NeurIPS 33, 18661\u201318673 (2020)","journal-title":"NeurIPS"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: CVPR, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"8_CR17","unstructured":"Li, F., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: CVPR, pp. 178\u2013178 (2004)"},{"issue":"9","key":"8_CR18","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. CSUR 55(9), 1\u201335 (2023)","journal-title":"CSUR"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Cristian, R.O., Damien, T., Stephen, G.: Image retrieval on real-life images with pre-trained vision-and-language models. In: ICCV, pp. 2125\u20132134 (2021)","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"8_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). arXiv:1711.05101"},{"key":"8_CR21","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft (2013). arXiv:1306.5151"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGPI, pp. 722\u2013729 (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR, pp. 3498\u20133505 (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Parmar, G., Kumar\u00a0Singh, K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: SIGGRAPH, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"8_CR25","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"8_CR26","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022). arXiv:2204.06125"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Bilen, H., Vedaldi, A.: Efficient parametrization of multi-domain deep neural networks. In: CVPR, pp. 8119\u20138127 (2018)","DOI":"10.1109\/CVPR.2018.00847"},{"key":"8_CR28","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imagenet classifiers generalize to imagenet? In: ICML, pp. 5389\u20135400 (2019)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Saito, K., Sohn, K., Zhang, X., Li, C.L., Lee, C.Y., Saenko, K., Pfister, T.: Pic2word: mapping pictures to words for zero-shot composed image retrieval. In: CVPR, pp. 19305\u201319314 (2023)","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: CVPR, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"8_CR31","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild (2012). arXiv:1212.0402"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Sun, Q., Liu, Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: CVPR, pp. 403\u2013412 (2019)","DOI":"10.1109\/CVPR.2019.00049"},{"key":"8_CR33","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. NeurIPS 32 (2019)"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yu, L., Qiang, L., et\u00a0al: CRIS: CLIP-driven referring image segmentation. In: CVPR, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"8_CR35","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: Simvlm: simple visual language model pretraining with weak supervision (2021). arXiv:2108.10904"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Wu, G., Chen, J., Zhang, W., Wang, R.: Feature adaptation with clip for few-shot classification. In: ACM MMAsia, pp.\u00a01\u20137 (2023)","DOI":"10.1145\/3595916.3626396"},{"key":"8_CR37","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, pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Yu, T., Lu, Z., Jin, X., Chen, Z., Wang, X.: Task residual for tuning vision-language models. In: CVPR, pp. 10899\u201310909 (2023)","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai, J., Qiao, Y., Li, H.: Tip-adapter: training-free adaption of clip for few-shot classification. In: ECCV, pp. 493\u2013510 (2022)","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, C., Hu, X., He, Z.: Unsupervised prototype adapter for vision-language models. In: PRCV, pp. 197\u2013209 (2023)","DOI":"10.1007\/978-981-99-8429-9_16"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"8_CR42","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. IJCV 130(9), 2337\u20132348 (2022)","journal-title":"IJCV"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, B., Zhu, Y., Yang, X., Chen, C., Xu, J.: Shifted diffusion for text-to-image generation. In: CVPR, pp. 10157\u201310166 (2023)","DOI":"10.1109\/CVPR52729.2023.00979"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8502-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:17:31Z","timestamp":1730384251000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8502-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819785018","9789819785025"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8502-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}