{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:57:28Z","timestamp":1772834248004,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":45,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543830","type":"print"},{"value":"9789819543847","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4384-7_27","type":"book-chapter","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T15:42:55Z","timestamp":1762357375000},"page":"384-395","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain Generalization with\u00a0CLIP-Based Multi-modal Calibration Distillation"],"prefix":"10.1007","author":[{"given":"Zhiyu","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dandan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,6]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Addepalli, S., Asokan, A.R., Sharma, L., Babu, R.V.: Leveraging vision-language models for improving domain generalization in image classification. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52733.2024.02258"},{"key":"27_CR2","doi-asserted-by":"publisher","unstructured":"Beery, S., Van Horn, G., Perona, P.: Recognition in Terra Incognita. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 472\u2013489. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_28","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"27_CR3","unstructured":"Cha, J., et al.: Swad: domain generalization by seeking flat minima. In: Neural Information Processing Systems (2021)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Cha, J., Lee, K., Park, S., Chun, S.: Domain generalization by mutual-information regularization with pre-trained models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20050-2_26"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, W., Zhao, Z., Su, F., Men, A., Dong, Y.: Instance paradigm contrastive learning for domain generalization. IEEE Trans. Circuits Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2023.3289201"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, W., Zhao, Z., Su, F., Men, A., Meng, H.: Practicaldg: perturbation distillation on vision-language models for hybrid domain generalization. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02218"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Cho, J., Nam, G., Kim, S., Yang, H., Kwak, S.: Promptstyler: prompt-driven style generation for source-free domain generalization. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01439"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Dai, W., Hou, L., Shang, L., Jiang, X., Liu, Q., Fung, P.: Enabling multimodal generation on clip via vision-language knowledge distillation. In: Findings (2022)","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Fang, C., Xu, Y., Rockmore, D.N.: Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias. In: 2013 IEEE International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.208"},{"key":"27_CR10","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: Clip2video: Mastering video-text retrieval via image clip. In: ArXiv (2021)"},{"key":"27_CR11","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: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01853"},{"key":"27_CR12","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference on Learning Representations (2021)"},{"key":"27_CR13","unstructured":"Gulrajani, I., Lopez-Paz, D.: In search of lost domain generalization. In: ArXiv (2020)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Guo, J., Qi, L., Shi, Y.: Domaindrop: Suppressing domain-sensitive channels for domain generalization. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01751"},{"key":"27_CR15","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Neural Information Processing Systems (2015)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhou, A., Lin, Z., Cai, M., Wang, H., Lee, Y.J.: A sentence speaks a thousand images: Domain generalization through distilling clip with language guidance. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01073"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Jain, S., Addepalli, S., Sahu, P.K., Dey, P., Babu, R.V.: Dart: diversify-aggregate-repeat training improves generalization of neural networks. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01540"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Kang, J., Lee, S., Kim, N.W., Kwak, S.: Style neophile: constantly seeking novel styles for domain generalization. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00699"},{"key":"27_CR19","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Communications of the ACM (2012)"},{"key":"27_CR20","unstructured":"Kumar, A., Raghunathan, A., Jones, R.M., Ma, T., Liang, P.: Fine-tuning can distort pretrained features and underperform out-of-distribution. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net (2022)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Lee, K., Kim, S., Kwak, S.: Cross-domain ensemble distillation for domain generalization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19806-9_1"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.591"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Li, H., Pan, S.J., Wang, S., Kot, A.C.: Domain generalization with adversarial feature learning. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00566"},{"key":"27_CR24","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, PMLR (17\u201323 Jul 2022)"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Li, X., Fang, Y., Liu, M., Ling, Z., Tu, Z., Su, H.: Distilling large vision-language model with out-of-distribution generalizability. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00236"},{"key":"27_CR26","unstructured":"Li, Y., Liang, F., Zhao, L., Cui, Y., Ouyang, W., Shao, J., Yu, F., Yan, J.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. In: The Tenth International Conference on Learning Representations, ICLR (2021)"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Lv, F., Liang, J., Li, S., Zang, B., Liu, C.H., Wang, Z., Liu, D.: Causality inspired representation learning for domain generalization. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"27_CR28","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: International Conference on Learning Representations (2022)"},{"key":"27_CR29","unstructured":"Muandet, K., Balduzzi, D., Sch\u00f6lkopf, B.: Domain generalization via invariant feature representation. In: Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28. ICML\u201913, JMLR.org (2013)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Pei, R., zhuo Liu, J., Li, W., Shao, B., Xu, S., Dai, P., Lu, J., Yan, Y.: Clipping: Distilling clip-based models with a student base for video-language retrieval. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"27_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Proceedings of Machine Learning Research, PMLR (2021)"},{"key":"27_CR32","unstructured":"Shu, M., Nie, W., Huang, D.A., Yu, Z., Goldstein, T., Anandkumar, A., Xiao, C.: Test-time prompt tuning for zero-shot generalization in vision-language models. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems. Curran Associates, Inc. (2022)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Shu, Y., Cao, Z., Wang, C., Wang, J., Long, M.: Open domain generalization with domain-augmented meta-learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00950"},{"key":"27_CR34","unstructured":"Shu, Y., Guo, X., Wu, J., Wang, X., Wang, J., Long, M.: Clipood: Generalizing clip to out-of-distributions. In: International Conference on Machine Learning (2023)"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Flava: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15638\u201315650 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Sun, B., Saenko, K.: Deep coral: Correlation alignment for deep domain adaptation. In: ECCV Workshops (2016)","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Venkateswara, H., Eus\u00e9bio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.572"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, H., Chau, L.P., Kot, A.C.: Embracing the dark knowledge: Domain generalization using regularized knowledge distillation. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475434"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et al.: Robust fine-tuning of zero-shot models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhang, R., Zhang, Y., Wang, Y., Tian, Q.: A fourier-based framework for domain generalization. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01415"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., Zhang, Q.: Cross-image relational knowledge distillation for semantic segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yang, L., Zheng, Y.: Translating and segmenting multimodal medical volumes with cycle- and shape-consistency generative adversarial network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00963"},{"key":"27_CR43","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. In: International booktitle of Computer Vision (2021)"},{"key":"27_CR44","doi-asserted-by":"publisher","unstructured":"Zhou, K., Yang, Y., Hospedales, T., Xiang, T.: Learning to generate novel domains for domain generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 561\u2013578. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_33","DOI":"10.1007\/978-3-030-58517-4_33"},{"key":"27_CR45","unstructured":"Zhou, K., Yang, Y., Qiao, Y., Xiang, T.: Domain generalization with mixstyle. In: International Conference on Learning Representations (2021)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4384-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T14:06:33Z","timestamp":1772805993000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4384-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,6]]},"ISBN":["9789819543830","9789819543847"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4384-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,6]]},"assertion":[{"value":"6 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}