{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:02:41Z","timestamp":1757628161330,"version":"3.44.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032028129"},{"type":"electronic","value":"9783032028136"}],"license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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\/978-3-032-02813-6_5","type":"book-chapter","created":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T07:15:29Z","timestamp":1756624529000},"page":"62-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the\u00a0Domain Robustness of\u00a0Contrastive Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3327-7404","authenticated-orcid":false,"given":"Mario","family":"Koddenbrock","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5363-0278","authenticated-orcid":false,"given":"Rudolf","family":"Hoffmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7664-4389","authenticated-orcid":false,"given":"David","family":"Brodmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3711-1498","authenticated-orcid":false,"given":"Erik","family":"Rodner","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863","volume":"28","author":"W Al-Dhabyani","year":"2020","unstructured":"Al-Dhabyani, W., Gomaa, M., Khaled, H., Fahmy, A.: Dataset of breast ultrasound images. Data Brief 28, 104863 (2020)","journal-title":"Data Brief"},{"key":"5_CR2","unstructured":"Ali, R.B., Ejbali, R., Zaied, M.: Detection and classification of dental caries in x-ray images using deep neural networks. In: International Conference on Software Engineering Advances (ICSEA), p.\u00a0236 (2016)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Baby, M., Jereesh, A.: Automatic nerve segmentation of ultrasound images. In: 2017 International Conference of Electronics, Communication and Aerospace Technology (ICECA), vol.\u00a01, pp. 107\u2013112. IEEE (2017)","DOI":"10.1109\/ICECA.2017.8203654"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTEC AD\u2013A comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9592\u20139600 (2019)","DOI":"10.1109\/CVPR.2019.00982"},{"key":"5_CR5","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"5_CR6","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":"5_CR7","unstructured":"Chapelle, O., Weston, J., Bottou, L., Vapnik, V.: Vicinal risk minimization. In: Advances in Neural Information Processing Systems, vol. 13 (2000)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"5_CR9","unstructured":"Croce, F., et al.: RobustBench: a standardized adversarial robustness benchmark. arXiv preprint arXiv:2010.09670 (2020)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"5_CR11","unstructured":"Duchi, J.C., Hashimoto, T., Namkoong, H.: Distributionally robust losses against mixture covariate shifts. Under Rev. 2(1) (2019)"},{"key":"5_CR12","unstructured":"Fang, A., et al.: Data determines distributional robustness in contrastive language image pre-training (clip). In: International Conference on Machine Learning, pp. 6216\u20136234. PMLR (2022)"},{"key":"5_CR13","unstructured":"Garg, S., Erickson, N., Sharpnack, J., Smola, A., Balakrishnan, S., Lipton, Z.C.: RLSbench: domain adaptation under relaxed label shift. In: International Conference on Machine Learning, pp. 10879\u201310928. PMLR (2023)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"5_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/978-3-642-42051-1_16","volume-title":"Neural Information Processing","author":"IJ Goodfellow","year":"2013","unstructured":"Goodfellow, I.J., et al.: Challenges in representation learning: a report on three machine learning contests. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8228, pp. 117\u2013124. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-42051-1_16"},{"key":"5_CR16","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"issue":"2","key":"5_CR17","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1148\/radiol.2018180736","volume":"290","author":"SS Halabi","year":"2019","unstructured":"Halabi, S.S., et al.: The RSNA pediatric bone age machine learning challenge. Radiology 290(2), 498\u2013503 (2019)","journal-title":"Radiology"},{"issue":"3","key":"5_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10994-025-06742-z","volume":"114","author":"Z Han","year":"2025","unstructured":"Han, Z., et al.: Alignclip: navigating the misalignments for robust vision-language generalization. Mach. Learn. 114(3), 1\u201319 (2025). https:\/\/doi.org\/10.1007\/s10994-025-06742-z","journal-title":"Mach. Learn."},{"key":"5_CR19","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the International Conference on Learning Representations (2019)"},{"key":"5_CR20","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"5_CR21","doi-asserted-by":"publisher","first-page":"9920","DOI":"10.1109\/ACCESS.2023.3240216","volume":"11","author":"Y Joo","year":"2023","unstructured":"Joo, Y., Park, H.C., Lee, O.J., Yoon, C., Choi, M.H., Choi, C.: Classification of liver fibrosis from heterogeneous ultrasound image. IEEE Access 11, 9920\u20139930 (2023)","journal-title":"IEEE Access"},{"key":"5_CR22","doi-asserted-by":"publisher","unstructured":"Kar, O.F., Tonioni, A., Poklukar, P., Kulshrestha, A., Zamir, A., Tombari, F.: Brave: broadening the visual encoding of vision-language models. In: European Conference on Computer Vision, pp. 113\u2013132. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-72640-8_7","DOI":"10.1007\/978-3-031-72640-8_7"},{"key":"5_CR23","unstructured":"Koh, P.W., et\u00a0al.: Wilds: a benchmark of in-the-wild distribution shifts. In: International conference on machine learning, pp. 5637\u20135664. PMLR (2021)"},{"issue":"1","key":"5_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2017.177","volume":"4","author":"RS Lee","year":"2017","unstructured":"Lee, R.S., Gimenez, F., Hoogi, A., Miyake, K.K., Gorovoy, M., Rubin, D.L.: A curated mammography data set for use in computer-aided detection and diagnosis research. Sci. Data 4(1), 1\u20139 (2017)","journal-title":"Sci. Data"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Li, K., Lu, J., Zuo, H., Zhang, G.: Source-free multi-domain adaptation with generally auxiliary model training. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892718"},{"key":"5_CR26","unstructured":"Lim, S., Kim, I., Kim, T., Kim, C., Kim, S.: Fast Autoaugment. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"5_CR27","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: International Conference on Learning Representations (2018)"},{"key":"5_CR28","unstructured":"Maharana, S.K., Zhang, B., Karlinsky, L., Feris, R., Guo, Y.: Enhancing robustness of clip to common corruptions through bimodal test-time adaptation. arXiv preprint arXiv:2412.02837 (2024)"},{"key":"5_CR29","unstructured":"OpenAI: GPT-4 technical report. https:\/\/openai.com\/research\/gpt-4 (2023). Accessed 9 Jan 2025"},{"key":"5_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"5_CR31","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s44196-024-00615-4","volume":"17","author":"AM Sarhan","year":"2024","unstructured":"Sarhan, A.M., et al.: Knee osteoporosis diagnosis based on deep learning. Int. J. Comput. Intell. Syst. 17(1), 241 (2024)","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"5_CR32","first-page":"18583","volume":"33","author":"R Taori","year":"2020","unstructured":"Taori, R., Dave, A., Shankar, V., Carlini, N., Recht, B., Schmidt, L.: Measuring robustness to natural distribution shifts in image classification. Adv. Neural Inf. Process. Syst. (NeurIPS) 33, 18583\u201318599 (2020)","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"5_CR33","doi-asserted-by":"publisher","unstructured":"Vapnik, V.: The Nature of Statistical Learning Theory. Springer Science & Business Media (1999). https:\/\/doi.org\/10.1007\/978-1-4757-3264-1","DOI":"10.1007\/978-1-4757-3264-1"},{"issue":"5","key":"5_CR34","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1109\/72.788640","volume":"10","author":"VN Vapnik","year":"1999","unstructured":"Vapnik, V.N.: An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988\u2013999 (1999)","journal-title":"IEEE Trans. Neural Netw."},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Verma, P., Van, M.H., Wu, X.: Beyond human vision: the role of large vision language models in microscope image analysis. arXiv preprint arXiv:2405.00876 (2024)","DOI":"10.1109\/BigData62323.2024.10825000"},{"key":"5_CR36","unstructured":"Wang, Q., Lin, Y., Chen, Y., Schmidt, L., Han, B., Zhang, T.: A sober look at the robustness of clips to spurious features. arXiv preprint arXiv:2403.11497 (2024)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"5_CR38","unstructured":"Wolf, T., et\u00a0al.: HuggingFace\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"issue":"7","key":"5_CR39","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","volume":"55","author":"GS Xia","year":"2017","unstructured":"Xia, G.S., et al.: AID: a benchmark data set for performance evaluation of aerial scene classification. IEEE Trans. Geosci. Remote Sens. 55(7), 3965\u20133981 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"5_CR40","unstructured":"Xu, H., et al.: Demystifying clip data. In: 12th International Conference on Learning Representations, ICLR 2024 (2024)"},{"key":"5_CR41","unstructured":"Yin, D., Gontijo\u00a0Lopes, R., Shlens, J., Cubuk, E.D., Gilmer, J.: A fourier perspective on model robustness in computer vision. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Ma, M., Wang, K., Qin, Z., Yue, X., You, Y.: Preventing zero-shot transfer degradation in continual learning of vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19125\u201319136 (2023)","DOI":"10.1109\/ICCV51070.2023.01752"}],"container-title":["Lecture Notes in Computer Science","KI 2025: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02813-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T06:02:29Z","timestamp":1757484149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02813-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"ISBN":["9783032028129","9783032028136"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02813-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"assertion":[{"value":"1 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing financial or non-financial interests related to this work. This research was conducted independently and is not affiliated with or endorsed by any of the organizations that developed the evaluated models or datasets.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"KI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Artificial Intelligence (K\u00fcnstliche Intelligenz)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Potsdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ki2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ki2025.gi.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}