{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T05:24:55Z","timestamp":1749878695182,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819786190"},{"type":"electronic","value":"9789819786206"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-981-97-8620-6_12","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"173-186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-layer Tuning CLIP for Few-Shot Image Classification"],"prefix":"10.1007","author":[{"given":"Ruihao","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jinsong","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Cenyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zunlei","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Liang","family":"xue","sequence":"additional","affiliation":[]},{"given":"Yijun","family":"Bei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, X., Ma, Z., Xue, J.-H.: Deep metric learning for few-shot image classification: a review of recent developments. Pattern Recognit. 138, 109381 (2023)","DOI":"10.1016\/j.patcog.2023.109381"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Feuz, K.Y., Cook, D.J.: Transfer learning across feature-rich heterogeneous feature spaces via feature-space remapping (FSR). ACM Trans. Intell. Syst. Technol. (TIST) 6(1), 1\u201327 (2015)","DOI":"10.1145\/2629528"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Liu, W., Chang, X., Yan, Y., Yang, Y., Hauptmann, A.G.: Few-shot text and image classification via analogical transfer learning. ACM Trans. Intell. Syst. Technol. (TIST) 9(6), 1\u201320 (2018)","DOI":"10.1145\/3230709"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1717\u20131724 (2014)","DOI":"10.1109\/CVPR.2014.222"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chu, W.H., Li, Y.J., Chang, J.C., Wang, Y.C.F.: Spot and learn: a maximum-entropy patch sampler for few-shot image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6251\u20136260 (2019)","DOI":"10.1109\/CVPR.2019.00641"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Sun, Q., Liu, Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 403\u2013412 (2019)","DOI":"10.1109\/CVPR.2019.00049"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Alfassy, A., Karlinsky, L., Aides, A., Shtok, J., Harary, S., Feris, R., Giryes, R., Bronstein, A.M.: Laso: label-set operations networks for multi-label few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6548\u20136557 (2019)","DOI":"10.1109\/CVPR.2019.00671"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Peng, Z., Li, Z., Zhang, J., Li, Y., Qi, G.J., Tang, J.: Few-shot image recognition with knowledge transfer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 441\u2013449 (2019)","DOI":"10.1109\/ICCV.2019.00053"},{"key":"12_CR9","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: International Conference on Machine Learning. PMLR, pp 8748\u20138763"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"He, R., Liu, L., Ye, H., Tan, Q., Ding, B., Cheng, L., Low, J.W., Bing, L., Si, L.: On the effectiveness of adapter-based tuning for pretrained language model adaptation (2021). arXiv:2106.03164","DOI":"10.18653\/v1\/2021.acl-long.172"},{"key":"12_CR11","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De Laroussilhe, Q., Gesmundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning (2021). arXiv:2104.08691","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Y., Kordi, Y., Mishra, S., Liu, A., Smith, N.A., Khashabi, D., Hajishirzi, H.: Self-instruct: aligning language models with self-generated instructions (2022). arXiv:2212.10560","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Zhu, B., Niu, Y., Han, Y., Wu, Y., Zhang, H.: Prompt-aligned gradient for prompt tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp.15659\u201315669 (2023)","DOI":"10.1109\/ICCV51070.2023.01435"},{"issue":"2","key":"12_CR16","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., Qiao, Yu.: Clip-adapter: better vision-language models with feature adapters. Int. J. Comput. Vision 132(2), 581\u2013595 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"12_CR17","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: European Conference on Computer Vision, pp. 493\u2013510. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhang, R., He, B., Zhou, A., Wang, D., Zhao, B., Gao, P.: Not all features matter: enhancing few-shot clip with adaptive prior refinement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2605\u20132615 (2023)","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: Vqa: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Lee, D., Song, S., Suh, J., Choi, J., Lee, S., Kim, H.J.: Read-only prompt optimization for vision-language few-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1401\u20131411 (2023)","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"12_CR21","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models (2022). arXiv:2210.07183"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Pratt, S., Covert, I., Liu, R., Farhadi, A.: What does a platypus look like? generating customized prompts for zero-shot image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15691\u201315701 (2023)","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Maniparambil, M., Vorster, C., Molloy, D., Murphy, N., McGuinness, K., O\u2019Connor, N.E.: Enhancing clip with GPT-4: Harnessing visual descriptions as prompts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 262\u2013271 (2023)","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Gondal, M.W., Gast, J., Ruiz, I.A., Droste, R., Macri, T., Kumar, S., Staudigl, L.: Domain aligned clip for few-shot classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5721\u20135730 (2024)","DOI":"10.1109\/WACV57701.2024.00562"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Yan, J., Xie, Y., Guo, Y., Wei, Y., Zhang, X., Luan, X.: Cocoopter: pre-train, prompt, and fine-tune the vision-language model for few-shot image classification. Int. J. Multimed. Inf. Retrieval 12(2), 27 (2023)","DOI":"10.1007\/s13735-023-00286-5"},{"key":"12_CR26","first-page":"746","volume":"37","author":"Z Guo","year":"2023","unstructured":"Guo, Z., Zhang, R., Qiu, L., Ma, X., Miao, X., He, X., Cui, B.: Calip: zero-shot enhancement of clip with parameter-free attention. Proc. AAAI Conf. Artif. Intell. 37, 746\u2013754 (2023)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Lin, Z., Yu, S., Kuang, Z., Pathak, D., Ramanan, D.: Multimodality helps unimodality: Cross-modal few-shot learning with multimodal models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19325\u201319337 (2023)","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"12_CR28","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"12_CR29","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: 2004 Conference on Computer Vision and Pattern Recognition Workshop, pp. 178\u2013178. IEEE (2004)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Nilsback, M-E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp.722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101\u2013mining discriminative components with random forests. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13, pp. 446\u2013461. Springer (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"12_CR34","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft (2013). arXiv:1306.5151"},{"key":"12_CR35","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: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"12_CR36","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":"12_CR37","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"issue":"7","key":"12_CR38","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","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. IEEE J. Sel. Topics Appl. Earth Observat. Remote Sens. 12(7), 2217\u20132226 (2019)","journal-title":"IEEE J. Sel. Topics Appl. Earth Observat. Remote Sens."},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Silva-Rodriguez, J., Hajimiri, S., Ben Ayed, I., Dolz, J.: A closer look at the few-shot adaptation of large vision-language models (2023). arXiv:2312.12730","DOI":"10.1109\/CVPR52733.2024.02235"}],"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\/978-981-97-8620-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:17:41Z","timestamp":1736885861000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 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"}}]}}