{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:47:07Z","timestamp":1785797227905,"version":"3.56.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032315823","type":"print"},{"value":"9783032315830","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"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\/978-3-032-31583-0_6","type":"book-chapter","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:24:27Z","timestamp":1785795867000},"page":"77-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CoAttn-PEFT: Complementary Attention in\u00a0Parameter-Efficient Fine-Tuning for\u00a0Improved Adaptation and\u00a0Generalization"],"prefix":"10.1007","author":[{"given":"Chushan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinguang","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Ba\u0142azy, K., Banaei, M., Aberer, K., Tabor, J.: Lora-xs: low-rank adaptation with extremely small number of parameters. arXiv preprint arXiv:2405.17604 (2024)","DOI":"10.3233\/FAIA251185"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van\u00a0Gool, 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, Cham (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"6_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"6_CR5","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":"6_CR6","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: Qlora: efficient finetuning of quantized llms. Adv. Neural. Inf. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-0441"},{"key":"6_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"6_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"6_CR9","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Proc. Syst. 30 (2017)"},{"key":"6_CR10","unstructured":"Fu, C., et al.: Mme: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"issue":"1","key":"6_CR11","first-page":"307","volume":"13","author":"MU Gutmann","year":"2012","unstructured":"Gutmann, M.U., Hyv\u00e4rinen, A.: Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics. J. Mach. Learn. Res. 13(1), 307\u2013361 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR12","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR14","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"6_CR15","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"6_CR16","unstructured":"Hu, J.Y.C., Su, M., Kuo, E.J., Song, Z., Liu, H.: Computational limits of low-rank adaptation (lora) fine-tuning for transformer models. In: ICLR 2025 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy (2025)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: FPT: improving prompt tuning efficiency via progressive training. arXiv preprint arXiv:2211.06840 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.511"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"6_CR19","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: European Conference on Computer Vision, pp. 709\u2013727. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"6_CR21","unstructured":"Kalajdzievski, D.: Scaling laws for forgetting when fine-tuning large language models. arXiv preprint arXiv:2401.05605 (2024)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"6_CR23","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15190\u201315200 (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything (2023). arXiv:2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"6_CR25","unstructured":"Kopiczko, D.J., Blankevoort, T., Asano, Y.M.: Vera: vector-based random matrix adaptation. arXiv preprint arXiv:2310.11454 (2023)"},{"key":"6_CR26","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":"6_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23390\u201323400 (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, X., Fu, X., Zhang, X., Wang, W., Yang, J.: Promptkd: unsupervised prompt distillation for vision-language models. arXiv preprint arXiv:2403.02781 (2024)","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: Lora dropout as a sparsity regularizer for overfitting control. arXiv preprint arXiv:2404.09610 (2024)","DOI":"10.1016\/j.knosys.2025.114241"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Lingam, V., et al.: Svft: Parameter-efficient fine-tuning with singular vectors. arXiv preprint arXiv:2405.19597 (2024)","DOI":"10.52202\/079017-1311"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-1516"},{"key":"6_CR33","unstructured":"Liu, S.Y., et al.: Dora: weight-decomposed low-rank adaptation. arXiv preprint arXiv:2402.09353 (2024)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, J., Zhang, Y., Liu, Y., Tian, X.: Prompt distribution learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5206\u20135215 (2022)","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"6_CR35","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"6_CR36","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":"6_CR37","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: 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":"6_CR38","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR39","unstructured":"Roy, S., Etemad, A.: Consistency-guided prompt learning for vision-language models. arXiv preprint arXiv:2306.01195 (2023)"},{"key":"6_CR40","unstructured":"Sanyal, A., Torr, P.H., Dokania, P.K.: Stable rank normalization for improved generalization in neural networks and gans. arXiv preprint arXiv:1906.04659 (2019)"},{"key":"6_CR41","unstructured":"Sclar, M., Choi, Y., Tsvetkov, Y., Suhr, A.: Quantifying language models\u2019 sensitivity to spurious features in prompt design or: how i learned to start worrying about prompt formatting. arXiv preprint arXiv:2310.11324 (2023)"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"6_CR43","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"6_CR44","doi-asserted-by":"publisher","first-page":"75623","DOI":"10.52202\/075280-3305","volume":"36","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Chauhan, J., Wang, W., Hsieh, C.J.: Universality and limitations of prompt tuning. Adv. Neural. Inf. Process. Syst. 36, 75623\u201375643 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR45","doi-asserted-by":"publisher","first-page":"61060","DOI":"10.52202\/075280-2669","volume":"36","author":"J Wu","year":"2023","unstructured":"Wu, J., et al.: Infoprompt: information-theoretic soft prompt tuning for natural language understanding. Adv. Neural. Inf. Process. Syst. 36, 61060\u201361084 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR46","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: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., Xu, C.: Visual-language prompt tuning with knowledge-guided context optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6757\u20136767 (2023)","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"6_CR48","unstructured":"Zhang, C., Lu, R., Tong, J., Wang, Y., Li, H.: 3d-ide: 3d implicit depth emergent. arXiv preprint arXiv:2604.03296 (2026)"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, C., Tong, J., Lin, T.J., Nguyen, C., Li, H.: PMVC: promoting multi-view consistency for 3d scene reconstruction. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3678\u20133688 (2024)","DOI":"10.1109\/WACV57701.2024.00364"},{"key":"6_CR50","doi-asserted-by":"publisher","first-page":"21442","DOI":"10.52202\/068431-1558","volume":"35","author":"H Zhang","year":"2022","unstructured":"Zhang, H., Li, G., Li, J., Zhang, Z., Zhu, Y., Jin, Z.: Fine-tuning pre-trained language models effectively by optimizing subnetworks adaptively. Adv. Neural. Inf. Process. Syst. 35, 21442\u201321454 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR51","unstructured":"Zhang, Q., et al.: Adaptive budget allocation for parameter-efficient fine-tuning. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"6_CR52","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"},{"issue":"9","key":"6_CR53","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. Int. J. Comput. Vis. 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31583-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:24:32Z","timestamp":1785795872000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31583-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"ISBN":["9783032315823","9783032315830"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31583-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"assertion":[{"value":"4 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"}}]}}