{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:45:51Z","timestamp":1779385551992,"version":"3.53.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045577","type":"print"},{"value":"9783032045584","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"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\/978-3-032-04558-4_20","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:16:44Z","timestamp":1757589404000},"page":"247-259","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["CIBR: Cross-Modal Information Bottleneck Regularization for\u00a0Robust CLIP Generalization"],"prefix":"10.1007","author":[{"given":"Yingrui","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaofei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenrui","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aokun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiansheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"20_CR1","unstructured":"Alayrac, J.B., et al.: Self-supervised multimodal versatile networks. In: NeurIPS (2020)"},{"key":"20_CR2","unstructured":"Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. arXiv:1612.00410 (2016)"},{"key":"20_CR3","unstructured":"Bahng, H., Jahanian, A., Sankaranarayanan, S., Isola, P.: Visual prompting: modifying pixel space to adapt pre-trained models. arXiv:2203.17274 (2022)"},{"key":"20_CR4","unstructured":"Belghazi, M.I., et al.: Mutual information neural estimation. In: International Conference on Machine Learning, pp. 531\u2013540. PMLR (2018)"},{"key":"20_CR5","unstructured":"Chen, T., et al.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"20_CR6","unstructured":"Di\u00a0Wu, S.L., et al.: Align yourself: self-supervised pre-training for fine-grained recognition via saliency alignment. arXiv:2106.15788, vol. 2, no. 7, p. 8 (2021)"},{"key":"20_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"issue":"1","key":"20_CR8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1109\/JSAIT.2020.2991561","volume":"1","author":"Z Goldfeld","year":"2020","unstructured":"Goldfeld, Z., Polyanskiy, Y.: The information bottleneck problem and its applications in machine learning. IEEE J. Sel. Areas Inf. Theory 1(1), 19\u201338 (2020)","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Han, C., et al.: E2VPT: an effective and efficient approach for visual prompt tuning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01604"},{"key":"20_CR10","unstructured":"HaoChen, J.Z., Wei, C., Gaidon, A., Ma, T.: Provable guarantees for self-supervised deep learning with spectral contrastive loss. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) NeurIPS (2021)"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"20_CR12","unstructured":"Ji, Y., Kaza, V.S., Artham, N., Wang, T.: Deep active learning with manifold-preserving trajectory sampling. arXiv:2410.15605 (2024)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Ji, Y., Zhu, Y., Li, Z., Chen, J., Kong, Y., Chen, J.: Enhancing out-of-distribution detection through dynamic activation function. In: ICASSP 2025, pp.\u00a01\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10890331"},{"key":"20_CR14","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916. PMLR (2021)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"20_CR16","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":"20_CR17","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: ICML (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"20_CR18","unstructured":"van\u00a0den Oord, A., et al.: Representation learning with contrastive predictive coding. arXiv:1807.03748 (2018)"},{"key":"20_CR19","unstructured":"Qi, D., Su, L., Song, J., Cui, E., et\u00a0al.: ImageBERT: cross-modal pre-training with large-scale weak-supervised image-text data. arXiv:2001.07966 (2020)"},{"key":"20_CR20","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"20_CR21","unstructured":"Saunshi, N., et al.: Understanding contrastive learning requires incorporating inductive biases. In: ICML, pp. 19250\u201319286. PMLR (2022)"},{"issue":"12","key":"20_CR22","doi-asserted-by":"publisher","first-page":"124020","DOI":"10.1088\/1742-5468\/ab3985","volume":"2019","author":"AM Saxe","year":"2019","unstructured":"Saxe, A.M., et al.: On the information bottleneck theory of deep learning. J. Stat. Mech: Theory Exp. 2019(12), 124020 (2019)","journal-title":"J. Stat. Mech: Theory Exp."},{"key":"20_CR23","unstructured":"Shwartz-Ziv, R., Tishby, N.: Opening the black box of deep neural networks via information. arXiv:1703.00810 (2017)"},{"key":"20_CR24","unstructured":"Sun, Q., Fang, Y., Wu, L.Y., Wang, X., Cao, Y.: EVA-CLIP: improved training techniques for CLIP at scale. In: CVPR (2023)"},{"key":"20_CR25","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. In: Proceedings of the 37th Annual Allerton Conference on Communication, Control and Computing, pp. 368\u2013377 (2000)"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: 2015 IEEE Information Theory Workshop (ITW), pp.\u00a01\u20135. IEEE (2015)","DOI":"10.1109\/ITW.2015.7133169"},{"key":"20_CR27","unstructured":"Tsai, Y.H.H., et al.: Conditional contrastive learning with kernel. arXiv:2202.05458 (2022)"},{"key":"20_CR28","unstructured":"Tschannen, M., et al.: On mutual information maximization for representation learning. arXiv:1907.13625 (2019)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Wang, F., Liu, H.: Understanding the behaviour of contrastive loss. In: CVPR, pp. 2495\u20132504 (2021)","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Wang, K., Herranz, L., van\u00a0de Weijer, J.: Continual learning in cross-modal retrieval. In: CVPR, pp. 3628\u20133638 (2021)","DOI":"10.1109\/CVPRW53098.2021.00402"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: M2 PT: multimodal prompt tuning for zero-shot instruction learning. arXiv:2409.15657 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.218"},{"key":"20_CR32","unstructured":"Wang, Y., Zhang, Q., Wang, Y., Yang, J., Lin, Z.: Chaos is a ladder: a new theoretical understanding of contrastive learning via augmentation overlap (2022)"},{"key":"20_CR33","unstructured":"Wang, Z., et al.: Connecting multi-modal contrastive representations. In: NeurIPS, vol. 36, pp. 22099\u201322114 (2023)"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Xiao, X., et al.: TD-RD: a top-down benchmark with real-time framework for road damage detection (2025)","DOI":"10.1109\/ICASSP49660.2025.10888616"},{"key":"20_CR35","unstructured":"Xiao, X., et al.: Visual variational autoencoder prompt tuning (2025)"},{"key":"20_CR36","unstructured":"Yao, L., Huang, R., Hou, L., Lu, G., et\u00a0al.: FILIP: fine-grained interactive language-image pre-training. In: ICLR (2022)"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Zhai, X., Wang, X., Mustafa, B., Steiner, A., Keysers, D., et\u00a0al.: LiT: zero-shot transfer with locked-image text tuning. In: CVPR, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"20_CR39","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. In: CVPR, pp. 16816\u201316825 (2022)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04558-4_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:16:53Z","timestamp":1757589413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04558-4_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045577","9783032045584"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04558-4_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}