{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T11:49:21Z","timestamp":1777204161259,"version":"3.51.4"},"reference-count":90,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,7,13]],"date-time":"2025-07-13T00:00:00Z","timestamp":1752364800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,13]],"date-time":"2025-07-13T00:00:00Z","timestamp":1752364800000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11263-025-02527-y","type":"journal-article","created":{"date-parts":[[2025,7,13]],"date-time":"2025-07-13T12:01:01Z","timestamp":1752408061000},"page":"7076-7109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Bayes-CAL: Robust Cross-Modal Alignment by Bayesian Approach for Few-Shot OoD Generalization"],"prefix":"10.1007","volume":"133","author":[{"given":"Lin","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihan","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinying","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinbing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenghu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3129-3953","authenticated-orcid":false,"given":"Nanyang","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"2527_CR1","unstructured":"Ahuja, K., Shanmugam, K., & Varshney, K., et\u00a0al. (2020). Invariant risk minimization games. In International Conference on Machine Learning, PMLR, pp. 145\u2013155"},{"key":"2527_CR2","doi-asserted-by":"crossref","unstructured":"Akuzawa K., Iwasawa Y., Matsuo Y. (2019). Adversarial invariant feature learning with accuracy constraint for domain generalization. In: ECML-PKDD","DOI":"10.1007\/978-3-030-46147-8_19"},{"key":"2527_CR3","unstructured":"Arjovsky, M., Bottou, L., & Gulrajani I., et\u00a0al. (2019). Invariant risk minimization. arXiv preprint arXiv:1907.02893"},{"key":"2527_CR4","doi-asserted-by":"crossref","unstructured":"Bai, H., Sun, R., & Hong, L., et\u00a0al. (2020). Decaug: Out-of-distribution generalization via decomposed feature representation and semantic augmentation. arXiv preprint arXiv:2012.09382.","DOI":"10.1609\/aaai.v35i8.16829"},{"key":"2527_CR5","doi-asserted-by":"crossref","unstructured":"Bai, H., Sun, R., & Hong, L., et\u00a0al. (2021). Decaug: Out-of-distribution generalization via decomposed feature representation and semantic augmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6705\u20136713.","DOI":"10.1609\/aaai.v35i8.16829"},{"key":"2527_CR6","first-page":"412","volume":"403","author":"D Berrar","year":"2018","unstructured":"Berrar, D. (2018). Bayes\u2019 Theorem and Naive Bayes Classifier. Encyclopedia of Bioinformatics and Computational Biology: ABC of Bioinformatics, 403, 412.","journal-title":"Encyclopedia of Bioinformatics and Computational Biology: ABC of Bioinformatics"},{"issue":"1","key":"2527_CR7","first-page":"46","volume":"22","author":"G Blanchard","year":"2021","unstructured":"Blanchard, G., Deshmukh, A. A., Dogan, \u00dc., et al. (2021). Domain Generalization by Marginal Transfer Learning. The Journal of Machine Learning Research, 22(1), 46\u2013100.","journal-title":"The Journal of Machine Learning Research"},{"issue":"518","key":"2527_CR8","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","volume":"112","author":"DM Blei","year":"2017","unstructured":"Blei, D. M., Kucukelbir, A., & McAuliffe, J. D. (2017). Variational Inference: A Review for Statisticians. Journal of the American statistical Association, 112(518), 859\u2013877.","journal-title":"Journal of the American statistical Association"},{"key":"2527_CR9","unstructured":"Chen, W.Y., Liu, Y.C., & Kira, Z., et\u00a0al. (2019). A closer look at few-shot classification. arXiv preprint arXiv:1904.04232."},{"key":"2527_CR10","unstructured":"Chen, Y., Zhou, K., & Bian, Y., et\u00a0al. (2022). Pareto invariant risk minimization: Towards mitigating the optimization dilemma in out-of-distribution generalization. arXiv preprint arXiv:2206.07766."},{"key":"2527_CR11","unstructured":"Ch\u00e9rief-Abdellatif, B.E. (2019). Consistency of elbo maximization for model selection. In Symposium on Advances in Approximate Bayesian Inference, PMLR, pp. 11\u201331."},{"key":"2527_CR12","doi-asserted-by":"publisher","first-page":"2995","DOI":"10.1214\/18-EJS1475","volume":"12","author":"BE Ch\u00e9rief-Abdellatif","year":"2018","unstructured":"Ch\u00e9rief-Abdellatif, B. E., & Alquier, P. (2018). Consistency of Variational Bayes Inference for Estimation and Model Selection in Mixtures. Electronic Journal of Statistics, 12, 2995\u20133035.","journal-title":"Electronic Journal of Statistics"},{"key":"2527_CR13","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., & Ramos, S., et\u00a0al. (2016) The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"2527_CR14","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q. V., et al. (2021). Coatnet: Marrying Convolution and Attention for All Data Sizes. Advances in Neural Information Processing Systems, 34, 3965\u20133977.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2527_CR15","unstructured":"Dou, Q., Castro, D.C., & Kamnitsas, K., et\u00a0al. (2019). Domain generalization via model-agnostic learning of semantic features. In NeurIPS."},{"key":"2527_CR16","doi-asserted-by":"crossref","unstructured":"Du, Y., Liu, Z., & Li, J., et\u00a0al. (2022). A survey of vision-language pre-trained models. arXiv preprint arXiv:2202.10936.","DOI":"10.24963\/ijcai.2022\/762"},{"key":"2527_CR17","doi-asserted-by":"crossref","unstructured":"Fan, Z., Ma, Y., & Li, Z., et\u00a0al. (2021). Generalized few-shot object detection without forgetting. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4527\u20134536.","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"2527_CR18","doi-asserted-by":"crossref","unstructured":"Fang, Z., Zhu, X., & Yang, C., et\u00a0al. (2022). Learning aligned cross-modal representation for generalized zero-shot classification. In Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6605\u20136613.","DOI":"10.1609\/aaai.v36i6.20614"},{"key":"2527_CR19","unstructured":"Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning, PMLR, pp. 1126\u20131135"},{"key":"2527_CR20","unstructured":"Gao, P., Geng, S., & Zhang, R., et\u00a0al. (2021). Clip-adapter: Better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544"},{"issue":"4","key":"2527_CR21","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1214\/17-BA1085","volume":"12","author":"P Gr\u00fcnwald","year":"2017","unstructured":"Gr\u00fcnwald, P., & van Ommen, T. (2017). Inconsistency of Bayesian Inference for Misspecified Linear Models, and a Proposal for Repairing It. Bayesian Analysis, 12(4), 1069\u20131103.","journal-title":"Bayesian Analysis"},{"key":"2527_CR22","doi-asserted-by":"crossref","unstructured":"Gu, Y., Han, X., & Liu, Z., et\u00a0al. (2021). Ppt: Pre-trained prompt tuning for few-shot learning. arXiv preprint arXiv:2109.04332","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"2527_CR23","unstructured":"Gulrajani, I., & Lopez-Paz, D. (2020). In search of lost domain generalization. arXiv preprint arXiv:2007.01434"},{"key":"2527_CR24","doi-asserted-by":"crossref","unstructured":"Guo, J., Wang, N., & Qi, L., et\u00a0al. (2023). Aloft: A lightweight mlp-like architecture with dynamic low-frequency transform for domain generalization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24,132\u201324,141.","DOI":"10.1109\/CVPR52729.2023.02311"},{"key":"2527_CR25","doi-asserted-by":"crossref","unstructured":"Guo, Y., Codella, N.C., & Karlinsky, L., et\u00a0al. (2020). A broader study of cross-domain few-shot learning. In European conference on computer vision, Springer, pp. 124\u2013141.","DOI":"10.1007\/978-3-030-58583-9_8"},{"key":"2527_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., & Ren, S., et\u00a0al. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2527_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., & Doll\u00e1r, P., et\u00a0al. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"issue":"107","key":"2527_CR28","first-page":"383","volume":"110","author":"Y He","year":"2021","unstructured":"He, Y., Shen, Z., & Cui, P. (2021). Towards Non-iid Image Classification: A Dataset and Baselines. Pattern Recognition, 110(107), 383.","journal-title":"Pattern Recognition"},{"key":"2527_CR29","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., & Mu, N., et\u00a0al. (2021a). The many faces of robustness: A critical analysis of out-of-distribution generalization. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138349.","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"2527_CR30","unstructured":"Hendrycks, D., Zhao, K., & Basart, S., et\u00a0al. (2021b). Natural adversarial examples. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15,262\u201315,271."},{"key":"2527_CR31","doi-asserted-by":"crossref","unstructured":"Huang Z., Wang H., Xing EP., et\u00a0al. (2020). Self-challenging improves cross-domain generalization. In: European Conference on Computer Vision, Springer, pp. 124\u2013140","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"2527_CR32","first-page":"3907","volume":"33","author":"T Jeong","year":"2020","unstructured":"Jeong, T., & Kim, H. (2020). Ood-maml: Meta-learning for Few-shot Out-of-distribution Detection and Classification. Advances in Neural Information Processing Systems, 33, 3907\u20133916.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2527_CR33","unstructured":"Jia C., Yang Y., Xia Y., et\u00a0al. (2021). Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, PMLR, pp. 4904\u20134916"},{"key":"2527_CR34","unstructured":"JIMIN L. (2022). crack detection_v2 dataset. Visited on 2023-03-27"},{"key":"2527_CR35","doi-asserted-by":"crossref","unstructured":"Jo SY., Yoon SW. (2023). Poem: Polarization of embeddings for domain-invariant representations. arXiv preprint arXiv:2305.13046","DOI":"10.1609\/aaai.v37i7.25984"},{"key":"2527_CR36","doi-asserted-by":"crossref","unstructured":"Johnson-Roberson M., Barto C., Mehta R., et\u00a0al. (2017). Driving in the matrix: Can virtual worlds replace human-generated annotations for real world tasks? In: 2017 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 746\u2013753","DOI":"10.1109\/ICRA.2017.7989092"},{"key":"2527_CR37","unstructured":"Kristiadi A., Hein M., Hennig P. (2022). Being a bit frequentist improves bayesian neural networks. In: International Conference on Artificial Intelligence and Statistics, PMLR, pp. 529\u2013545"},{"key":"2527_CR38","doi-asserted-by":"crossref","unstructured":"Lee S., Bae J., Kim HY. (2023). Decompose, adjust, compose: Effective normalization by playing with frequency for domain generalization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11,776\u201311,785","DOI":"10.1109\/CVPR52729.2023.01133"},{"key":"2527_CR39","doi-asserted-by":"crossref","unstructured":"Li D., Yang Y., Song YZ., et\u00a0al. (2017). Deeper, broader and artier domain generalization. In: Proceedings of the IEEE international conference on computer vision, pp. 5542\u20135550","DOI":"10.1109\/ICCV.2017.591"},{"key":"2527_CR40","unstructured":"Li J., Li D., Xiong C., et\u00a0al. (2022). Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International conference on machine learning, PMLR, pp. 12,888\u201312,900"},{"issue":"109","key":"2527_CR41","first-page":"548","volume":"119","author":"S Li","year":"2024","unstructured":"Li, S., Zhao, Q., Sun, B., et al. (2024). Domain Generalization via Causal Fine-grained Feature Decomposition and Learning. Computers and Electrical Engineering, 119(109), 548.","journal-title":"Computers and Electrical Engineering"},{"key":"2527_CR42","doi-asserted-by":"crossref","unstructured":"Li X., Yin X., Li C., et\u00a0al. (2020). Oscar: Object-semantics aligned pre-training for vision-language tasks. In: European Conference on Computer Vision, Springer, pp. 121\u2013137","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"2527_CR43","unstructured":"Li Y., Wang H., Duan Y., et\u00a0al. (2023). Clip surgery for better explainability with enhancement in open-vocabulary tasks. arXiv e-prints pp. arXiv\u20132304"},{"key":"2527_CR44","doi-asserted-by":"crossref","unstructured":"Lin Y., Dong H., Wang H., et\u00a0al. (2022). Bayesian invariant risk minimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16,021\u201316,030","DOI":"10.1109\/CVPR52688.2022.01555"},{"key":"2527_CR45","unstructured":"Liu S., Chen T., Atashgahi Z., et\u00a0al. (2021). Deep ensembling with no overhead for either training or testing: The all-round blessings of dynamic sparsity. arXiv preprint arXiv:2106.14568"},{"key":"2527_CR46","doi-asserted-by":"crossref","unstructured":"Liu Z., Luo P., Wang X., et\u00a0al. (2015). Deep learning face attributes in the wild. In: Proceedings of the IEEE international conference on computer vision, pp. 3730\u20133738","DOI":"10.1109\/ICCV.2015.425"},{"key":"2527_CR47","unstructured":"Lu H., Yu Z., Niu X., et\u00a0al. (2023). Neuron structure modeling for generalizable remote physiological measurement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18,589\u201318,599"},{"key":"2527_CR48","unstructured":"Muandet K., Balduzzi D., Sch\u00f6lkopf B. (2013). Domain generalization via invariant feature representation. In: International conference on machine learning, PMLR, pp. 10\u201318"},{"key":"2527_CR49","unstructured":"Radford A., Kim JW., Hallacy C., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PMLR, pp. 8748\u20138763"},{"key":"2527_CR50","doi-asserted-by":"crossref","unstructured":"Rahman S., Khan S., Barnes N. (2020). Improved visual-semantic alignment for zero-shot object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11,932\u201311,939","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"2527_CR51","doi-asserted-by":"crossref","unstructured":"Rao Y., Zhao W., Chen G., et\u00a0al. (2022). Denseclip: Language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18,082\u201318,091","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"2527_CR52","unstructured":"Recht B., Roelofs R., Schmidt L., et\u00a0al. (2019). Do imagenet classifiers generalize to imagenet? In: International conference on machine learning, PMLR, pp. 5389\u20135400"},{"key":"2527_CR53","unstructured":"Rosenfeld E., Ravikumar P., Risteski A. (2020). The risks of invariant risk minimization. arXiv preprint arXiv:2010.05761"},{"key":"2527_CR54","unstructured":"Rusu AA., Rao D., Sygnowski J., et\u00a0al. (2018). Meta-learning with latent embedding optimization. arXiv preprint arXiv:1807.05960"},{"key":"2527_CR55","doi-asserted-by":"crossref","unstructured":"Sahu M., Str\u00f6msd\u00f6rfer R., Mukhopadhyay A., et\u00a0al. (2020). Endo-sim2real: Consistency learning-based domain adaptation for instrument segmentation. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23, Springer, pp. 784\u2013794","DOI":"10.1007\/978-3-030-59716-0_75"},{"issue":"12","key":"2527_CR56","doi-asserted-by":"publisher","first-page":"3434","DOI":"10.1109\/TITS.2016.2552248","volume":"17","author":"Y Shi","year":"2016","unstructured":"Shi, Y., Cui, L., Qi, Z., et al. (2016). Automatic Road Crack Detection Using Random Structured Forests. IEEE Transactions on Intelligent Transportation Systems, 17(12), 3434\u20133445.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"2527_CR57","doi-asserted-by":"crossref","unstructured":"Sung F., Yang Y., Zhang L., et\u00a0al. (2018). Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"2527_CR58","doi-asserted-by":"crossref","unstructured":"Torralba A., Efros AA. (2011). Unbiased look at dataset bias. In: CVPR 2011, IEEE, pp. 1521\u20131528","DOI":"10.1109\/CVPR.2011.5995347"},{"issue":"2","key":"2527_CR59","doi-asserted-by":"publisher","first-page":"2634","DOI":"10.1109\/LRA.2021.3062303","volume":"6","author":"J Truong","year":"2021","unstructured":"Truong, J., Chernova, S., & Batra, D. (2021). Bi-directional Domain Adaptation for Sim2real Transfer of Embodied Navigation Agents. IEEE Robotics and Automation Letters, 6(2), 2634\u20132641.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2527_CR60","doi-asserted-by":"crossref","unstructured":"Venkateswara H., Eusebio J., Chakraborty S., et\u00a0al. (2017). Deep hashing network for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5018\u20135027","DOI":"10.1109\/CVPR.2017.572"},{"key":"2527_CR61","unstructured":"Vuorio R., Sun SH., Hu H., et\u00a0al. (2019). Multimodal model-agnostic meta-learning via task-aware modulation. Advances in Neural Information Processing Systems 32"},{"key":"2527_CR62","unstructured":"Wang C., Jiang J., Zhou X., et\u00a0al. (2022a). Resmooth: Detecting and utilizing ood samples when training with data augmentation. IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2527_CR63","unstructured":"Wang H., Ge S., Lipton Z., et\u00a0al. (2019). Learning robust global representations by penalizing local predictive power. Advances in Neural Information Processing Systems 32"},{"key":"2527_CR64","unstructured":"Wang P., Yang A., Men R., et\u00a0al. (2022b). Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International conference on machine learning, PMLR, pp. 23,318\u201323,340"},{"key":"2527_CR65","unstructured":"Wang SJ., Johnson AM. (2021). Domain adaptation using system invariant dynamics models. In: Learning for Dynamics and Control, PMLR, pp. 1130\u20131141"},{"issue":"3","key":"2527_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","volume":"53","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Yao, Q., Kwok, J. T., et al. (2020). Generalizing from a Few Examples: A Survey on Few-shot Learning. ACM computing surveys (csur), 53(3), 1\u201334.","journal-title":"ACM computing surveys (csur)"},{"key":"2527_CR67","unstructured":"Wang Z., Grigsby J., Qi Y. (2023). Pgrad: Learning principal gradients for domain generalization. arXiv preprint arXiv:2305.01134"},{"key":"2527_CR68","doi-asserted-by":"crossref","unstructured":"Wehrmann J., Kolling C., Barros RC. (2020). Adaptive cross-modal embeddings for image-text alignment. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12,313\u201312,320","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"2527_CR69","first-page":"7181","volume":"35","author":"F Wenzel","year":"2022","unstructured":"Wenzel, F., Dittadi, A., Gehler, P., et al. (2022). Assaying Out-of-distribution Generalization in Transfer Learning. Advances in Neural Information Processing Systems, 35, 7181\u20137198.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2527_CR70","doi-asserted-by":"crossref","unstructured":"Wu C. (2022). The symmetry principle in condensed matter physics (i). In: A Festschrift in Honor of the CN Yang Centenary: Scientific Papers. World Scientific, p 413\u2013473","DOI":"10.1142\/9789811264153_0025"},{"key":"2527_CR71","doi-asserted-by":"crossref","unstructured":"Wu X., Zhu F., Zhao R., et\u00a0al. (2023). Cora: Adapting clip for open-vocabulary detection with region prompting and anchor pre-matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7031\u20137040","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"2527_CR72","unstructured":"Xu R., Cui P., Shen Z., et\u00a0al. (2021). Why stable learning works? a theory of covariate shift generalization. arXiv preprint arXiv:2111.02355 2"},{"key":"2527_CR73","doi-asserted-by":"crossref","unstructured":"Ye N., Li K., Hong L., et\u00a0al. (2021a). Ood-bench: Benchmarking and understanding out-of-distribution generalization datasets and algorithms. arXiv preprint arXiv:2106.03721","DOI":"10.1109\/CVPR52688.2022.00779"},{"key":"2527_CR74","doi-asserted-by":"crossref","unstructured":"Ye N., Tang J., Deng H., et\u00a0al. (2021b). Adversarial invariant learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 12,441\u201312,449","DOI":"10.1109\/CVPR46437.2021.01226"},{"key":"2527_CR75","unstructured":"Yi M., Hou L., Sun J., et\u00a0al. (2021). Improved ood generalization via adversarial training and pretraing. In: International Conference on Machine Learning, PMLR, pp. 11,987\u201311,997"},{"key":"2527_CR76","doi-asserted-by":"crossref","unstructured":"Yu F., Chen H., Wang X., et\u00a0al. (2020). Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2636\u20132645","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"2527_CR77","doi-asserted-by":"crossref","unstructured":"Yu W., Liu Y., Hua W., et\u00a0al. (2023). Turning a clip model into a scene text detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6978\u20136988","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"2527_CR78","doi-asserted-by":"crossref","unstructured":"Zhang M., Zhuang Z., Wang Z., et\u00a0al. (2023). Rotogbml: Towards out-of-distribution generalization for gradient-based meta-learning. arXiv preprint arXiv:2303.06679","DOI":"10.1109\/ICME57554.2024.10687395"},{"key":"2527_CR79","doi-asserted-by":"crossref","unstructured":"Zhang P., Li X., Hu X., et\u00a0al. (2021a). Vinvl: Revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"2527_CR80","unstructured":"Zhang R., Fang R., Gao P., et\u00a0al. (2021b). Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930"},{"key":"2527_CR81","unstructured":"Zhang X., Iwasawa Y., Matsuo Y., et\u00a0al. (2021c). Amortized prompt: Guide clip to domain transfer learning. arXiv preprint arXiv:2111.12853"},{"key":"2527_CR82","doi-asserted-by":"crossref","unstructured":"Zhao S., Zhang Z., Schulter S., et\u00a0al. (2022). Exploiting unlabeled data with vision and language models for object detection. In: European conference on computer vision, Springer, pp. 159\u2013175","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"2527_CR83","doi-asserted-by":"crossref","unstructured":"Zheng Y., Huang R., Han C., et\u00a0al. (2020). Background learnable cascade for zero-shot object detection. In: Proceedings of the Asian Conference on Computer Vision","DOI":"10.1007\/978-3-030-69535-4_7"},{"key":"2527_CR84","doi-asserted-by":"crossref","unstructured":"Zhou K., Yang J., Loy CC., et\u00a0al. (2022a). Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16,816\u201316,825","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"2527_CR85","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., et al. (2022). Learning to Prompt for Vision-language Models. International Journal of Computer Vision, 130(9), 2337\u20132348.","journal-title":"International Journal of Computer Vision"},{"key":"2527_CR86","unstructured":"Zhou L. (2022). Mars\/lunar crater dataset. Visited on 2023-03-28"},{"key":"2527_CR87","doi-asserted-by":"crossref","unstructured":"Zhou X., Girdhar R., Joulin A., et\u00a0al. (2022c). Detecting twenty-thousand classes using image-level supervision. In: European conference on computer vision, Springer, pp. 350\u2013368","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"2527_CR88","unstructured":"Zhou X., Lin Y., Zhang W., et\u00a0al. (2022d). Sparse invariant risk minimization. In: International Conference on Machine Learning, PMLR, pp. 27,222\u201327,244"},{"key":"2527_CR89","doi-asserted-by":"crossref","unstructured":"Zhu C., Chen F., Ahmed U., et\u00a0al. (2021). Semantic relation reasoning for shot-stable few-shot object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8782\u20138791","DOI":"10.1109\/CVPR46437.2021.00867"},{"key":"2527_CR90","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yin, W., Yang, Y., et al. (2024). Vision-language Alignment Learning Under Affinity and Divergence Principles for Few-shot Out-of-distribution Generalization. International Journal of Computer Vision,132(9), 3375\u20133407.","DOI":"10.1007\/s11263-024-02036-4"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02527-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02527-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02527-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T08:53:57Z","timestamp":1760086437000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02527-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":90,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["2527"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02527-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"15 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}