{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:03Z","timestamp":1766068083024,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726668"},{"type":"electronic","value":"9783031726675"}],"license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"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\/978-3-031-72667-5_21","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:11:48Z","timestamp":1727554308000},"page":"369-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Dropout Mixture Low-Rank Adaptation for\u00a0Visual Parameters-Efficient Fine-Tuning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0579-5370","authenticated-orcid":false,"given":"Zhengyi","family":"Fang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9494-9836","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-3358","authenticated-orcid":false,"given":"Ran","family":"Yi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-4341","authenticated-orcid":false,"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"21_CR1","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"21_CR3","unstructured":"Chen, S., et al.: Adaptformer: adapting vision transformers for scalable visual recognition. Adv. Neural. Inf. Process. Syst. 35, 16664\u201316678 (2022)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Ding, N., et al.: Parameter-efficient fine-tuning of large-scale pre-trained language models. Nat. Mach. Intell. 5(3), 220\u2013235 (2023)","DOI":"10.1038\/s42256-023-00626-4"},{"key":"21_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"21_CR6","unstructured":"Dou, S., et\u00a0al.: The art of balancing: revolutionizing mixture of experts for maintaining world knowledge in language model alignment. arXiv preprint arXiv:2312.09979 (2023)"},{"key":"21_CR7","unstructured":"Edalati, A., Tahaei, M.S., Kobyzev, I., Nia, V.P., Clark, J.J., Rezagholizadeh, M.: Krona: parameter efficient tuning with kronecker adapter. arXiv preprint arXiv:2212.10650 (2022)"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Gebru, T., Krause, J., Wang, Y., Chen, D., Deng, J., Fei-Fei, L.: Fine-grained car detection for visual census estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a031 (2017)","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"21_CR9","doi-asserted-by":"publisher","unstructured":"Guo, D., Rush, A.M., Kim, Y.: Parameter-efficient transfer learning with diff pruning. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 4884\u20134896. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/V1\/2021.ACL-LONG.378","DOI":"10.18653\/V1\/2021.ACL-LONG.378"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Han, C., et al.: E 2 VPT: an effective and efficient approach for visual prompt tuning. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17445\u201317456. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.01604"},{"key":"21_CR11","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=0RDcd5Axok"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"21_CR14","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"21_CR15","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"21_CR16","doi-asserted-by":"publisher","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"21_CR17","unstructured":"Jie, S., Deng, Z.H.: Convolutional bypasses are better vision transformer adapters. arXiv preprint arXiv:2207.07039 (2022)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Jie, S., Deng, Z.H.: Fact: Factor-tuning for lightweight adaptation on vision transformer. Proc. AAAI Conf. Artif. Intell. 37, 1060\u20131068 (2023)","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"21_CR19","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: stanford dogs. In: Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC), vol.\u00a02. Citeseer (2011)"},{"key":"21_CR20","doi-asserted-by":"publisher","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event\/Punta Cana, 7\u201311 November 2021, pp. 3045\u20133059. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/V1\/2021.EMNLP-MAIN.243","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.243"},{"key":"21_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"21_CR22","doi-asserted-by":"publisher","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 4582\u20134597. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/V1\/2021.ACL-LONG.353","DOI":"10.18653\/V1\/2021.ACL-LONG.353"},{"key":"21_CR23","unstructured":"Lialin, V., Deshpande, V., Rumshisky, A.: Scaling down to scale up: a guide to parameter-efficient fine-tuning. arXiv preprint arXiv:2303.15647 (2023)"},{"key":"21_CR24","unstructured":"Lian, D., Zhou, D., Feng, J., Wang, X.: Scaling & shifting your features: a new baseline for efficient model tuning. In: NeurIPS (2022). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/00bb4e415ef117f2dee2fc3b778d806d-Abstract-Conference.html"},{"key":"21_CR25","unstructured":"Lin, W., et al.: Hierarchical side-tuning for vision transformers. arXiv preprint arXiv:2310.05393 (2023)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR27","unstructured":"Luo, G., et al.: Towards efficient visual adaption via structural re-parameterization. arXiv preprint arXiv:2302.08106 (2023)"},{"key":"21_CR28","doi-asserted-by":"publisher","unstructured":"Mao, Y., et al.: Unipelt: a unified framework for parameter-efficient language model tuning. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, 22\u201327 May 2022, pp. 6253\u20136264. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/V1\/2022.ACL-LONG.433","DOI":"10.18653\/V1\/2022.ACL-LONG.433"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Mercea, O.B., Gritsenko, A., Schmid, C., Arnab, A.: Time-memory-and parameter-efficient visual adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5536\u20135545 (2024)","DOI":"10.1109\/CVPR52733.2024.00529"},{"key":"21_CR30","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 and Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"21_CR31","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., Kamath, A., R\u00fcckl\u00e9, A., Cho, K., Gurevych, I.: Adapterfusion: non-destructive task composition for transfer learning. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 487\u2013503 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"21_CR33","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"R\u00fcckl\u00e9, A., et al.: Adapterdrop: on the efficiency of adapters in transformers. arXiv preprint arXiv:2010.11918 (2020)","DOI":"10.18653\/v1\/2021.emnlp-main.626"},{"key":"21_CR35","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 595\u2013604 (2015)","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"21_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"21_CR38","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"21_CR40","unstructured":"Wang, Y., Mukherjee, S., Liu, X., Gao, J., Awadallah, A.H., Gao, J.: Adamix: mixture-of-adapter for parameter-efficient tuning of large language models"},{"key":"21_CR41","unstructured":"Zaken, E.B., Ravfogel, S., Goldberg, Y.: Bitfit: simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)"},{"key":"21_CR42","unstructured":"Zhai, X., et\u00a0al.: A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867 (2019)"},{"key":"21_CR43","unstructured":"Zhang, Y., Zhou, K., Liu, Z.: Neural prompt search (2022)"}],"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\/978-3-031-72667-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:17:15Z","timestamp":1727554635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72667-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031726668","9783031726675"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72667-5_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"29 September 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"}}]}}