{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:31:20Z","timestamp":1772119880785,"version":"3.50.1"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728891","type":"print"},{"value":"9783031728907","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-3-031-72890-7_9","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:46:36Z","timestamp":1733514396000},"page":"138-154","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SAFT: Towards Out-of-Distribution Generalization in\u00a0Fine-Tuning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9193-1908","authenticated-orcid":false,"given":"Bac","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3158-4945","authenticated-orcid":false,"given":"Stefan","family":"Uhlich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2921-4873","authenticated-orcid":false,"given":"Fabien","family":"Cardinaux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9212-899X","authenticated-orcid":false,"given":"Lukas","family":"Mauch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1269-1190","authenticated-orcid":false,"given":"Marzieh","family":"Edraki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6223-0301","authenticated-orcid":false,"given":"Aaron","family":"Courville","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"9_CR1","unstructured":"Aghajanyan, A., Zettlemoyer, L., Gupta, S.: Intrinsic dimensionality explains the effectiveness of language model fine-tuning. In: ACL, pp. 7319\u20137328 (2020)"},{"key":"9_CR2","unstructured":"Arora, S., Ge, R., Neyshabur, B., Zhang, Y.: Stronger generalization bounds for deep nets via a compression approach. In: ICML, pp. 254\u2013263 (2018)"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van\u00a0Gool, L.: Food-101\u2013mining discriminative components with random forests. In: ECCV, pp. 446\u2013461 (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., Shah, R.: Signature verification using a \u201csiamese\u201d time delay neural network. In: NIPS, pp. 737\u2013739 (1993)","DOI":"10.1142\/9789812797926_0003"},{"key":"9_CR5","unstructured":"Cheng, H., Zhang, M., Shi, J.Q.: A survey on deep neural network pruning-taxonomy, comparison, analysis, and recommendations. arXiv preprint arXiv:2308.06767 (2023)"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"9_CR7","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: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"9_CR9","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: CVPR workshop, pp. 178\u2013178 (2004)"},{"key":"9_CR10","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: ICLR (2018)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Fu, Z., Yang, H., So, A.M.C., Lam, W., Bing, L., Collier, N.: On the effectiveness of parameter-efficient fine-tuning. In: AAAI, pp. 12799\u201312807 (2023)","DOI":"10.1609\/aaai.v37i11.26505"},{"key":"9_CR12","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. In: IJCV, pp. 1\u201315 (2023)"},{"key":"9_CR13","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: CVPR, pp. 19338\u201319347 (2023)","DOI":"10.1109\/CVPR52729.2023.01853"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Guo, D., Rush, A.M., Kim, Y.: Parameter-efficient transfer learning with diff pruning. In: ACL, pp. 4884\u20134896 (2021)","DOI":"10.18653\/v1\/2021.acl-long.378"},{"key":"9_CR15","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: NIPS (2015)"},{"key":"9_CR16","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":"9_CR17","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced bert with disentangled attention. In: ICLR (2021)"},{"key":"9_CR18","doi-asserted-by":"crossref","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. Top. Appl. Earth Obs. 12, 2217\u20132226 (2019)","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: CVPR, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"9_CR20","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":"12","key":"9_CR21","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/3467017","volume":"64","author":"S Hooker","year":"2021","unstructured":"Hooker, S.: The hardware lottery. Commun. ACM 64(12), 58\u201365 (2021)","journal-title":"Commun. ACM"},{"key":"9_CR22","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: ICML, pp. 2790\u20132799 (2019)"},{"key":"9_CR23","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: ICLR (2021)"},{"key":"9_CR24","unstructured":"Huang, T., Chu, J., Wei, F.: Unsupervised prompt learning for vision-language models. arXiv preprint arXiv:2204.03649 (2022)"},{"key":"9_CR25","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: CVPR, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"9_CR27","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114, 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Kornblith, S., Shlens, J., Le, Q.V.: Do better imagenet models transfer better? In: CVPR, pp. 2661\u20132671 (2019)","DOI":"10.1109\/CVPR.2019.00277"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: CVPR Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"9_CR30","unstructured":"Kumar, A., Raghunathan, A., Jones, R., Ma, T., Liang, P.: Fine-tuning can distort pretrained features and underperform out-of-distribution. In: ICLR (2022)"},{"key":"9_CR31","unstructured":"Li, C., Farkhoor, H., Liu, R., Yosinski, J.: Measuring the intrinsic dimension of objective landscapes. In: ICLR (2018)"},{"key":"9_CR32","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MM.2023.3256384","volume":"43","author":"S Lie","year":"2023","unstructured":"Lie, S.: Cerebras architecture deep dive: first look inside the hardware\/software co-design for deep learning. IEEE Micro 43, 18\u201330 (2023)","journal-title":"IEEE Micro"},{"key":"9_CR33","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"9_CR34","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"9_CR35","unstructured":"Miller, J.P., et al.: Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization. In: ICML, pp. 7721\u20137735 (2021)"},{"key":"9_CR36","unstructured":"Nikdan, M., Pegolotti, T., Iofinova, E., Kurtic, E., Alistarh, D.: Sparseprop: efficient sparse backpropagation for faster training of neural networks at the edge. In: ICML (2023)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGIP, pp. 722\u2013729 (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"9_CR38","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Parkhi, O., Vedaldi, A., Jawahar, C., Zisserman, A.: Cats and dogs. In: CVPR, pp. 3498\u20133505 (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"9_CR40","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: NIPS-W (2017)"},{"key":"9_CR41","doi-asserted-by":"publisher","first-page":"126658","DOI":"10.1016\/j.neucom.2023.126658","volume":"555","author":"H Pham","year":"2023","unstructured":"Pham, H., et al.: Combined scaling for zero-shot transfer learning. Neurocomputing 555, 126658 (2023)","journal-title":"Neurocomputing"},{"key":"9_CR42","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"9_CR43","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21, 5485\u20135551 (2020)","journal-title":"JMLR"},{"key":"9_CR44","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imagenet classifiers generalize to imagenet? In: ICML, pp. 5389\u20135400 (2019)"},{"key":"9_CR45","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, 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"9_CR46","unstructured":"Shu, M., et al.: Test-time prompt tuning for zero-shot generalization in vision-language models. In: NIPS, pp. 14274\u201314289 (2022)"},{"key":"9_CR47","unstructured":"Shu, Y., Guo, X., Wu, J., Wang, X., Wang, J., Long, M.: Clipood: generalizing clip to out-of-distributions. In: ICML, pp. 31716\u201331731 (2023)"},{"key":"9_CR48","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":"9_CR49","unstructured":"Sung, Y.L., Nair, V., Raffel, C.A.: Training neural networks with fixed sparse masks. In: NeurIPS, vol.\u00a034, pp. 24193\u201324205 (2021)"},{"key":"9_CR50","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7836\u20137845, June 2023","DOI":"10.1109\/CVPR52729.2023.00757"},{"key":"9_CR51","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"9_CR52","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: NIPS (2019)"},{"key":"9_CR53","unstructured":"Wang, Z., Liang, J., He, R., Xu, N., Wang, Z., Tan, T.: Improving zero-shot generalization for clip with synthesized prompts. In: ICCV, pp. 3032\u20133042 (2023)"},{"key":"9_CR54","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 (2022)"},{"key":"9_CR55","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":"9_CR56","doi-asserted-by":"crossref","unstructured":"Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning-the good, the bad and the ugly. In: CVPR, pp. 4582\u20134591 (2017)","DOI":"10.1109\/CVPR.2017.328"},{"key":"9_CR57","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: CVPR, pp. 3485\u20133492 (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"9_CR58","doi-asserted-by":"crossref","unstructured":"Yang, D., Ghasemazar, A., Ren, X., Golub, M., Lemieux, G., Lis, M.: Procrustes: a dataflow and accelerator for sparse deep neural network training. In: Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 711\u2013724 (2020)","DOI":"10.1109\/MICRO50266.2020.00064"},{"key":"9_CR59","unstructured":"Yuan, L., et al.: Revisiting out-of-distribution robustness in NLP: benchmark, analysis, and LLMS evaluations. In: NeurIPS D &B Track (2023)"},{"key":"9_CR60","unstructured":"Zaken, E.B., Goldberg, Y., Ravfogel, S.: Bitfit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: ACL, pp.\u00a01\u20139 (2022)"},{"key":"9_CR61","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Lit: zero-shot transfer with locked-image text tuning. In: CVPR, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"9_CR62","unstructured":"Zhang, D., Ahuja, K., Xu, Y., Wang, Y., Courville, A.: Can subnetwork structure be the key to out-of-distribution generalization? In: ICML, pp. 12356\u201312367 (2021)"},{"key":"9_CR63","unstructured":"Zhang, R., et al.: Tip-adapter: training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930 (2021)"},{"key":"9_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"9_CR65","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. IJCV 130, 2337\u20132348 (2022)","journal-title":"IJCV"}],"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\/978-3-031-72890-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:04:38Z","timestamp":1733515478000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72890-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9783031728891","9783031728907"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72890-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 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"}}]}}