{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:39:28Z","timestamp":1771958368580,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727832","type":"print"},{"value":"9783031727849","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72784-9_12","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"207-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Model Stock: All We Need Is Just a\u00a0Few Fine-Tuned Models"],"prefix":"10.1007","author":[{"given":"Dong-Hwan","family":"Jang","sequence":"first","affiliation":[]},{"given":"Sangdoo","family":"Yun","sequence":"additional","affiliation":[]},{"given":"Dongyoon","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"12_CR1","unstructured":"Barbu, A., et al.: ObjectNet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In: NeurIPS (2019)"},{"key":"12_CR2","unstructured":"Beyer, L., H\u00e9naff, O.J., Kolesnikov, A., Zhai, X., Oord, A.V.D.: Are we done with ImageNet? arXiv preprint arXiv:2006.07159 (2020)"},{"key":"12_CR3","unstructured":"Cha, J., et al.: SWAD: domain generalization by seeking flat minima. In: NeurIPS, vol. 34, pp. 22405\u201322418 (2021)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: CVPRW, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"12_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"12_CR6","unstructured":"Gouk, H., Hospedales, T.M., Pontil, M.: Distance-based regularisation of deep networks for fine-tuning. arXiv preprint arXiv:2002.08253 (2020)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Goyal, S., Kumar, A., Garg, S., Kolter, Z., Raghunathan, A.: Finetune like you pretrain: improved finetuning of zero-shot vision models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19338\u201319347 (2023)","DOI":"10.1109\/CVPR52729.2023.01853"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: ICCV, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"12_CR10","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"},{"issue":"1","key":"12_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1997.9.1.1","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Flat minima. Neural Comput. 9(1), 1\u201342 (1997)","journal-title":"Neural Comput."},{"key":"12_CR12","unstructured":"Ilharco, G., Ribeiro, M.T., Wortsman, M., Schmidt, L., Hajishirzi, H., Farhadi, A.: Editing models with task arithmetic. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=6t0Kwf8-jrj"},{"key":"12_CR13","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)"},{"key":"12_CR14","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: generalization gap and sharp minima. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=H1oyRlYgg"},{"key":"12_CR15","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report (2009)"},{"key":"12_CR16","unstructured":"Kumar, A., Raghunathan, A., Jones, R., Ma, T., Liang, P.: Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054 (2022)"},{"key":"12_CR17","unstructured":"Ledoux, M.: The concentration of measure phenomenon. No.\u00a089, American Mathematical Society (2001)"},{"key":"12_CR18","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss landscape of neural nets. In: NeurIPS, vol. 31 (2018)"},{"key":"12_CR19","unstructured":"Li, T., Huang, Z., Tao, Q., Wu, Y., Huang, X.: Trainable weight averaging: efficient training by optimizing historical solutions. In: ICLR (2022)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"12_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"12_CR22","unstructured":"Maddox, W.J., Izmailov, P., Garipov, T., Vetrov, D.P., Wilson, A.G.: A simple baseline for Bayesian uncertainty in deep learning. In: NeurIPS, vol. 32 (2019)"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Mao, X., Chen, Y., Jia, X., Zhang, R., Xue, H., Li, Z.: Context-aware robust fine-tuning. IJCV (2023). https:\/\/doi.org\/10.1007\/s11263-023-01951-2","DOI":"10.1007\/s11263-023-01951-2"},{"key":"12_CR24","unstructured":"Nam, G., Heo, B., Lee, J.: Lipsum-FT: robust fine-tuning of zero-shot models using random text guidance. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"12_CR25","unstructured":"Oh, C., et al.: Towards calibrated robust fine-tuning of vision-language models (2024). https:\/\/arxiv.org\/abs\/2311.01723"},{"key":"12_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"12_CR27","unstructured":"Rame, A., et al.: WARM: on the benefits of weight averaged reward models. In: Forty-First International Conference on Machine Learning (2024). https:\/\/openreview.net\/forum?id=s7RDnNUJy6"},{"key":"12_CR28","unstructured":"Ram\u00e9, A., et al.: Warp: on the benefits of weight averaged rewarded policies (2024). https:\/\/arxiv.org\/abs\/2406.16768"},{"key":"12_CR29","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to ImageNet? In: ICML (2019)"},{"issue":"3","key":"12_CR30","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Tian, J., He, Z., Dai, X., Ma, C.Y., Liu, Y.C., Kira, Z.: Trainable projected gradient method for robust fine-tuning. In: CVPR, pp. 7836\u20137845 (2023)","DOI":"10.1109\/CVPR52729.2023.00757"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Tian, J., Liu, Y.C., Smith, J.S., Kira, Z.: Fast trainable projection for robust fine-tuning. In: NeurIPS (2023)","DOI":"10.1109\/CVPR52729.2023.00757"},{"key":"12_CR34","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: NeurIPS (2019)"},{"key":"12_CR35","unstructured":"Wortsman, M., et\u00a0al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In: ICML, pp. 23965\u201323998. PMLR (2022)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: CVPR, pp. 7959\u20137971 (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"12_CR37","unstructured":"Yadav, P., Tam, D., Choshen, L., Raffel, C., Bansal, M.: TIES-merging: resolving interference when merging models. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=xtaX3WyCj1"},{"key":"12_CR38","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)"}],"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\/978-3-031-72784-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:48:59Z","timestamp":1727596139000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72784-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727832","9783031727849"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72784-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 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"}}]}}