{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T13:10:08Z","timestamp":1748092208304,"version":"3.41.0"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031920882","type":"print"},{"value":"9783031920899","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92089-9_20","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:49:07Z","timestamp":1748090947000},"page":"318-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Architecture-Agnostic Unsupervised Gradient Regularization for\u00a0Parameter-Efficient Transfer Learning"],"prefix":"10.1007","author":[{"given":"Wenjie","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yabin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"20_CR1","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"20_CR2","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":"20_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28, 41\u201375 (1997)","journal-title":"Mach. Learn."},{"key":"20_CR4","unstructured":"Chavan, A., Liu, Z., Gupta, D., Xing, E., Shen, Z.: One-for-all: generalized LORA for parameter-efficient fine-tuning. arXiv preprint arXiv:2306.07967 (2023)"},{"key":"20_CR5","first-page":"16664","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen, S., Ge, C., Tong, Z., Wang, J., Song, Y., Wang, J., Luo, P.: AdaptFormer: adapting vision transformers for scalable visual recognition. Adv. Neural. Inf. Process. Syst. 35, 16664\u201316678 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"20_CR7","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. arxiv 2022. arXiv preprint arXiv:2205.08534"},{"key":"20_CR8","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":"20_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Evgeniou, T., Pontil, M.: Regularized multi\u2013task learning. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 109\u2013117 (2004)","DOI":"10.1145\/1014052.1014067"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Feng, C.M., Yu, K., Liu, Y., Khan, S., Zuo, W.: Diverse data augmentation with diffusions for effective test-time prompt tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2704\u20132714 (2023)","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Feng, Z., Xu, C., Tao, D.: Self-supervised representation learning by rotation feature decoupling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10364\u201310374 (2019)","DOI":"10.1109\/CVPR.2019.01061"},{"key":"20_CR13","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR (2017)"},{"key":"20_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-319-46493-0_36","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Ghifary","year":"2016","unstructured":"Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 597\u2013613. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_36"},{"key":"20_CR15","unstructured":"Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: Advances in Neural Information Processing Systems, vol. 17 (2004)"},{"key":"20_CR16","unstructured":"Guangyuan, S., Li, Q., Zhang, W., Chen, J., Wu, X.M.: Recon: reducing conflicting gradients from the root for multi-task learning. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"He, W., et al.: Unsupervised prompt tuning for text-driven object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2651\u20132661 (2023)","DOI":"10.1109\/ICCV51070.2023.00250"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"20_CR20","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"20_CR21","unstructured":"Hu, E.J., et al.: LORA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"20_CR22","unstructured":"Huang, T., Chu, J., Wei, F.: Unsupervised prompt learning for vision-language models. arXiv preprint arXiv:2204.03649 (2022)"},{"key":"20_CR23","doi-asserted-by":"publisher","unstructured":"Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: European Conference on Computer Vision. pp. 709\u2013727. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Jie, S., Deng, Z.H.: Fact: Factor-tuning for lightweight adaptation on vision transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1060\u20131068 (2023)","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"20_CR25","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"20_CR26","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"20_CR27","first-page":"109","volume":"35","author":"D Lian","year":"2022","unstructured":"Lian, D., Zhou, D., Feng, J., Wang, X.: Scaling & shifting your features: a new baseline for efficient model tuning. Adv. Neural. Inf. Process. Syst. 35, 109\u2013123 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR28","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":"20_CR29","unstructured":"Loedeman, J., Stol, M.C., Han, T., Asano, Y.M.: Prompt generation networks for efficient adaptation of frozen vision transformers. arXiv preprint arXiv:2210.06466 (2022)"},{"key":"20_CR30","unstructured":"Luo, G., et al.: Towards efficient visual adaption via structural re-parameterization. arXiv preprint arXiv:2302.08106 (2023)"},{"key":"20_CR31","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"20_CR32","unstructured":"Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999 (2018)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: A visual vocabulary for flower classification. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol.\u00a02, pp. 1447\u20131454. IEEE (2006)","DOI":"10.1109\/CVPR.2006.42"},{"key":"20_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"20_CR35","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":"20_CR36","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"key":"20_CR37","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to ImageNet? In: International Conference on Machine Learning, pp. 5389\u20135400. PMLR (2019)"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"20_CR39","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR40","first-page":"14274","volume":"35","author":"M Shu","year":"2022","unstructured":"Shu, M., et al.: Test-time prompt tuning for zero-shot generalization in vision-language models. Adv. Neural. Inf. Process. Syst. 35, 14274\u201314289 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208 (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"20_CR42","doi-asserted-by":"publisher","unstructured":"Tang, M., Jin, Z., Zou, L., Shiuan-Ni, L.: Learning to resolve conflicts in multi-task learning. In: International Conference on Artificial Neural Networks. pp. 477\u2013489. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-44213-1_40","DOI":"10.1007\/978-3-031-44213-1_40"},{"key":"20_CR43","unstructured":"Tanwisuth, K., Zhang, S., Zheng, H., He, P., Zhou, M.: POUF: prompt-oriented unsupervised fine-tuning for large pre-trained models. arXiv preprint arXiv:2305.00350 (2023)"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Tu, C.H., Mai, Z., Chao, W.L.: Visual query tuning: towards effective usage of intermediate representations for parameter and memory efficient transfer learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7725\u20137735 (2023)","DOI":"10.1109\/CVPR52729.2023.00746"},{"key":"20_CR45","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Wang, P., Zhang, Z., Lei, Z., Zhang, L.: Sharpness-aware gradient matching for domain generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3769\u20133778 (2023)","DOI":"10.1109\/CVPR52729.2023.00367"},{"key":"20_CR47","first-page":"5682","volume":"35","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Huang, Z., Hong, X.: S-prompts learning with pre-trained transformers: an Occam\u2019s razor for domain incremental learning. Adv. Neural. Inf. Process. Syst. 35, 5682\u20135695 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR48","unstructured":"Xu, C., Yang, S., Wang, Y., Wang, Z., Fu, Y., Xue, X.: Exploring efficient few-shot adaptation for vision transformers. arXiv preprint arXiv:2301.02419 (2023)"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"20_CR50","unstructured":"Yu, B.X., et\u00a0al.: Visual tuning. arXiv preprint arXiv:2305.06061 (2023)"},{"key":"20_CR51","first-page":"5824","volume":"33","author":"T Yu","year":"2020","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. Adv. Neural. Inf. Process. Syst. 33, 5824\u20135836 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR52","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":"20_CR53","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":"20_CR54","first-page":"38629","volume":"35","author":"M Zhang","year":"2022","unstructured":"Zhang, M., Levine, S., Finn, C.: Memo: test time robustness via adaptation and augmentation. Adv. Neural. Inf. Process. Syst. 35, 38629\u201338642 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR55","doi-asserted-by":"publisher","unstructured":"Zhang, R., et al.: Tip-adapter: Training-free adaption of clip for few-shot classification. In: In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13695, pp. 493\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_29","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"20_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, M., Li, R., Jia, K., Zhang, L.: Exact feature distribution matching for arbitrary style transfer and domain generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8035\u20138045 (2022)","DOI":"10.1109\/CVPR52688.2022.00787"},{"key":"20_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tang, H., Jia, K.: Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 233\u2013248 (2018)","DOI":"10.1007\/978-3-030-01237-3_15"},{"key":"20_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, W., Tang, H., Ma, Z., Zhou, K., Zhang, L.: Dual memory networks: a versatile adaptation approach for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28718\u201328728 (2024)","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"20_CR59","unstructured":"Zhang, Y., Zhou, K., Liu, Z.: Neural prompt search. arXiv preprint arXiv:2206.04673 (2022)"},{"key":"20_CR60","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92089-9_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:49:24Z","timestamp":1748090964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92089-9_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031920882","9783031920899"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92089-9_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}