{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T16:07:18Z","timestamp":1771344438594,"version":"3.50.1"},"reference-count":128,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"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":[[2026,2]]},"DOI":"10.1007\/s11263-025-02656-4","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:13:24Z","timestamp":1768547604000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Knowledge Transfer for Mitigating Spurious Correlations in Deep Learning"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7305-1779","authenticated-orcid":false,"given":"Xiaoling","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Zhemg","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Shikun","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"2656_CR1","unstructured":"Ahuja, K., Caballero, E., Zhang, D., Bengio, Y., Mitliagkas, I. & Rish, I. (2021). Invariance principle meets information bottleneck for out-of-distribution generalization. In: Proc. Adv. Neural Inf. Process. Syst., pp. 3438\u20133450."},{"issue":"1","key":"2656_CR2","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1006\/jmaa.1998.6252","volume":"234","author":"H Alzer","year":"1999","unstructured":"Alzer, H. (1999). On the cauchy-schwarz inequality. J. Math. Anal. Appl.,234(1), 6\u201314.","journal-title":"J. Math. Anal. Appl."},{"key":"2656_CR3","unstructured":"Antoniou, A., Storkey, A. & Edwards, H. (2017). Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340."},{"key":"2656_CR4","doi-asserted-by":"crossref","unstructured":"Arik, S.\u00d6. & Pfister, T. (2021). Tabnet: Attentive interpretable tabular learning. In: Proc. AAAI Conf. Artif. Intell., pp. 6679\u20136687.","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"2656_CR5","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I. & Lopez-Paz, D. (2019). Invariant risk minimization. arXiv preprint arXiv:1907.02893 ."},{"key":"2656_CR6","unstructured":"Arjovsky, M., Chintala, S. & Bottou, L. (2017). Wasserstein gan. arXiv preprint arXiv:1701.07875."},{"key":"2656_CR7","doi-asserted-by":"crossref","unstructured":"Bandi, P. & others. (2018). From detection of individual metastases to classification of lymph node status at the patient level: the camelyon17 challenge. IEEE Trans. Med. Imaging 38(2), 550\u2013560.","DOI":"10.1109\/TMI.2018.2867350"},{"key":"2656_CR8","unstructured":"Bengio, Y., L\u00e9onard, N. & Courville, A. (2013). Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432."},{"key":"2656_CR9","unstructured":"Berthelot, D., Carlini, N., Cubuk, E.D., Kurakin, A., Sohn, K., Zhang, H. & Raffel, C. (2020). Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR10","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A. & Raffel, C.A. (2019). Mixmatch: A holistic approach to semi-supervised learning. In: Proc. Adv. Neural Inf. Process. Syst., pp. 5049\u20135059."},{"key":"2656_CR11","doi-asserted-by":"crossref","unstructured":"Borkan, D., Dixon, L., Sorensen, J., Thain, N. & Vasserman, L. (2019). Nuanced metrics for measuring unintended bias with real data for text classification. In: Proc. World Wide Web Conf., pp. 491\u2013500.","DOI":"10.1145\/3308560.3317593"},{"key":"2656_CR12","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N. & Ma, T. (2019). Learning imbalanced datasets with label-distribution-aware margin loss. In: Proc. Adv. Neural Inf. Process. Syst., pp. 1567\u20131578."},{"key":"2656_CR13","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I. & Abbeel, P. (2016). Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In: Proc. Adv. Neural Inf. Process. Syst., pp. 2180\u20132188."},{"key":"2656_CR14","unstructured":"Chen, H., Tao, R., Fan, Y., Wang, Y., Wang, J., Schiele, B., Xie, X., Raj, B. & Savvides, M. (2023). Softmatch: Addressing the quantity-quality trade-off in semi-supervised learning. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR15","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhou, Y., Wu, D., Zhang, W., Zhou, Y., Li, B. & Wang, W. (2022). Imagine by reasoning: A reasoning-based implicit semantic data augmentation for long-tailed classification. In: Proc. AAAI Conf. Artif. Intell., pp. 356\u2013364.","DOI":"10.1609\/aaai.v36i1.19912"},{"key":"2656_CR16","doi-asserted-by":"crossref","unstructured":"Chew, O., Lin, H.-T., Chang, K.-W. & Huang, K.-H. (2024). Understanding and mitigating spurious correlations in text classification with neighborhood analysis. In: Findings of Assoc. Comput. Linguist.: ACL, pp. 1013\u20131025.","DOI":"10.18653\/v1\/2024.findings-eacl.68"},{"key":"2656_CR17","doi-asserted-by":"crossref","unstructured":"Christie, G., Fendley, N., Wilson, J. & Mukherjee, R. (2018). Functional map of the world. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6172\u20136180.","DOI":"10.1109\/CVPR.2018.00646"},{"key":"2656_CR18","unstructured":"Coates, A., Ng, A. & Lee, H. (2011). An analysis of single-layer networks in unsupervised feature learning. In: Proc. Int. Conf. Artif. Intell. Stat., pp. 215\u2013223."},{"key":"2656_CR19","doi-asserted-by":"crossref","unstructured":"Cover, T. & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Trans. Inf. Theory, 21\u201327.","DOI":"10.1109\/TIT.1967.1053964"},{"key":"2656_CR20","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J. & Le, Q.V. (2020). Randaugment: Practical automated data augmentation with a reduced search space. In: Workshop of IEEE Conf. Comput. Vis. Pattern Recognit., pp. 702\u2013703.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"2656_CR21","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.-Y., Song, Y. & Belongie, S. (2019). Class-balanced loss based on effective number of samples. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 9268\u20139277.","DOI":"10.1109\/CVPR.2019.00949"},{"key":"2656_CR22","doi-asserted-by":"crossref","unstructured":"Deng, X., Wang, W., Feng, F., Zhang, H., He, X. & Liao, Y. (2023). Counterfactual active learning for out-of-distribution generalization. In: Proc. Annu. Meeting Assoc. Comput. Linguistics, pp. 11362\u201311377.","DOI":"10.18653\/v1\/2023.acl-long.636"},{"key":"2656_CR23","unstructured":"Deng, Y., Yang, Y., Mirzasoleiman, B. & Gu, Q. (2024). Robust learning with progressive data expansion against spurious correlation. In: Proc. Adv. Neural Inf. Process. Syst., pp. 1390\u20131402."},{"key":"2656_CR24","unstructured":"Ding, W., Shi, L., Chi, Y. & Zhao, D. (2023). Seeing is not believing: Robust reinforcement learning against spurious correlation. In: Proc. Adv. Neural Inf. Process. Syst., pp. 66328\u201366363."},{"issue":"3","key":"2656_CR25","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/s11263-022-01723-4","volume":"131","author":"Y Fan","year":"2023","unstructured":"Fan, Y., Kukleva, A., Dai, D., & Schiele, B. (2023). Revisiting consistency regularization for semi-supervised learning. Int. J. Comput. Vision,131(3), 626\u2013643.","journal-title":"Int. J. Comput. Vision"},{"issue":"3","key":"2656_CR26","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/s11263-023-01916-5","volume":"132","author":"SS Ghosal","year":"2024","unstructured":"Ghosal, S. S., & Li, Y. (2024). Are vision transformers robust to spurious correlations? Int. J. Comput. Vision,132(3), 689\u2013709.","journal-title":"Int. J. Comput. Vision"},{"issue":"11","key":"2656_CR27","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative adversarial networks. Commun. ACM,63(11), 139\u2013144.","journal-title":"Commun. ACM"},{"key":"2656_CR28","doi-asserted-by":"crossref","unstructured":"Gupta, U., Dhamala, J., Kumar, V., Verma, A., Pruksachatkun, Y., Krishna, S., Gupta, R., Chang, K-W., Ver Steeg, G. & Galstyan, A. (2022). Mitigating gender bias in distilled language models via counterfactual role reversal. In: Findings of Assoc. Comput. Linguist.: ACL, pp. 658\u2013678.","DOI":"10.18653\/v1\/2022.findings-acl.55"},{"issue":"3","key":"2656_CR29","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1007\/s13042-022-01658-9","volume":"14","author":"M Han","year":"2023","unstructured":"Han, M., Wu, H., Chen, Z., Li, M., & Zhang, X. (2023). A survey of multi-label classification based on supervised and semi-supervised learning. Intl. J. Mach. Learn. Cybern.,14(3), 697\u2013724.","journal-title":"Intl. J. Mach. Learn. Cybern."},{"key":"2656_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep residual learning for image recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2656_CR31","doi-asserted-by":"crossref","unstructured":"Hong, Y., Han, S., Choi, K., Seo, S., Kim, B. & Chang, B. (2021). Disentangling label distribution for long-tailed visual recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6626\u20136636.","DOI":"10.1109\/CVPR46437.2021.00656"},{"key":"2656_CR32","doi-asserted-by":"crossref","unstructured":"Hong, Y., Zhang, J., Sun, Z. & Yan, K. (2022). Safa: Sample-adaptive feature augmentation for long-tailed image classification. In: Eur. Conf. Comput. Vis., pp. 587\u2013603.","DOI":"10.1007\/978-3-031-20053-3_34"},{"key":"2656_CR33","unstructured":"Hu, Z., Tan, B., Salakhutdinov, R.R., Mitchell, T.M. & Xing, E.P. (2019). Learning data manipulation for augmentation and weighting. In: Proc. Adv. Neural Inf. Process. Syst., pp. 15764\u201315775."},{"key":"2656_CR34","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L. & Weinberger, K.Q. (2017). Densely connected convolutional networks. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"issue":"12","key":"2656_CR35","doi-asserted-by":"publisher","first-page":"8704","DOI":"10.1109\/TPAMI.2019.2918284","volume":"44","author":"G Huang","year":"2019","unstructured":"Huang, G., Liu, Z., Pleiss, G., Van Der Maaten, L., & Weinberger, K. Q. (2019). Convolutional networks with dense connectivity. IEEE Trans. Pattern Anal. Mach. Intell.,44(12), 8704\u20138716.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2656_CR36","doi-asserted-by":"crossref","unstructured":"Iscen, A., Tolias, G., Avrithis, Y. & Chum, O. (2019). Label propagation for deep semi-supervised learning. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 5070\u20135079.","DOI":"10.1109\/CVPR.2019.00521"},{"key":"2656_CR37","doi-asserted-by":"crossref","unstructured":"Jamal, M.A., Brown, M., Yang, M.-H., Wang, L. & Gong, B. (2020). Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 7610\u20137619.","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"2656_CR38","doi-asserted-by":"crossref","unstructured":"Kim, E., Lee, J. & Choo, J. (2021). Biaswap: Removing dataset bias with bias-tailored swapping augmentation. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 14992\u201315001.","DOI":"10.1109\/ICCV48922.2021.01472"},{"key":"2656_CR39","unstructured":"Koh, P.W., & others. (2021). Wilds: A benchmark of in-the-wild distribution shifts. In: Proc. Int. Conf. Mach. Learn., pp. 5637\u20135664."},{"key":"2656_CR40","doi-asserted-by":"crossref","unstructured":"Krishna, R., & others. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"2656_CR41","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images. University of Toronto."},{"key":"2656_CR42","unstructured":"Krueger, D., & others. (2021). Out-of-distribution generalization via risk extrapolation (rex). In: Proc. Int. Conf. Mach. Learn., pp. 5815\u20135826."},{"key":"2656_CR43","unstructured":"Laine, S. & Aila, T. (2017). Temporal ensembling for semi-supervised learning. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR44","unstructured":"Lee, D.-H., & others. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop of Int. Conf. Mach. Learn., pp. 896\u2013901."},{"key":"2656_CR45","unstructured":"Lee, J., Kim, E., Lee, J., Lee, J. & Choo, J. (2021). Learning debiased representation via disentangled feature augmentation. In: Proc. Adv. Neural Inf. Process. Syst., pp. 25123\u201325133."},{"key":"2656_CR46","doi-asserted-by":"crossref","unstructured":"Li, S., Gong, K., Liu, C.-H., Wang, Y., Qiao, F. & Cheng, X. (2021). Metasaug: Meta semantic augmentation for long-tailed visual recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 5208\u20135217.","DOI":"10.1109\/CVPR46437.2021.00517"},{"key":"2656_CR47","doi-asserted-by":"crossref","unstructured":"Li, S., Gong, K., Liu, C.H., Wang, Y., Qiao, F. & Cheng, X. (2021). Metasaug: Meta semantic augmentation for long-tailed visual recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 5212\u20135221.","DOI":"10.1109\/CVPR46437.2021.00517"},{"key":"2656_CR48","doi-asserted-by":"crossref","unstructured":"Li, H., Pan, S.J., Wang, S. & Kot, A.C. (2018). Domain generalization with adversarial feature learning. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 5400\u20135409.","DOI":"10.1109\/CVPR.2018.00566"},{"key":"2656_CR49","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, F., Lim, S.-N., Belongie, S. & Weinberger, K.Q. (2021). On feature normalization and data augmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 12383\u201312392.","DOI":"10.1109\/CVPR46437.2021.01220"},{"key":"2656_CR50","unstructured":"Liang, W. & Zou, J. (2022). Metashift: A dataset of datasets for evaluating contextual distribution shifts and training conflicts. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR51","doi-asserted-by":"crossref","unstructured":"Lim, J., Kim, Y., Kim, B., Ahn, C., Shin, J., Yang, E. & Han, S. (2023). Biasadv: Bias-adversarial augmentation for model debiasing. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 3832\u20133841.","DOI":"10.1109\/CVPR52729.2023.00373"},{"key":"2656_CR52","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"2656_CR53","unstructured":"Liu, E.Z., Haghgoo, B., Chen, A. S., Raghunathan, A., Koh, P. W., Sagawa, S., Liang, P. & Finn, C. (2021). Just train twice: Improving group robustness without training group information. In: Proc. Int. Conf. Mach. Learn., pp. 6781\u20136792."},{"key":"2656_CR54","unstructured":"Liu, Y., Liang, J.C., Tang, R., Lee, Y., Rabbani, M., Dianat, S., Rao, R., Huang, L., Liu, D., Wang, Q. & others. (2025). Re-imagining multimodal instruction tuning: A representation view. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR55","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X. & Tang, X. (2016). Deep learning face attributes in the wild. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 3730\u20133738.","DOI":"10.1109\/ICCV.2015.425"},{"key":"2656_CR56","doi-asserted-by":"crossref","unstructured":"Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B. & Yu, S.X. (2019). Large-scale long-tailed recognition in an open world. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2537\u20132546.","DOI":"10.1109\/CVPR.2019.00264"},{"key":"2656_CR57","unstructured":"Liu, W., Wen, Y., Yu, Z. & Yang, M. (2016). Large-margin softmax loss for convolutional neural networks. In: Proc. Int. Conf. Mach. Learn., pp. 507\u2013516."},{"key":"2656_CR58","unstructured":"Loh, C., Dangovski, R., Sudalairaj, S., Han, S., Han, L., Karlinsky, L., Soljacic, M. & Srivastava, A. (2022). On the importance of calibration in semi-supervised learning. arXiv preprint arXiv:2210.04783 ."},{"issue":"1","key":"2656_CR59","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.gltp.2022.04.020","volume":"3","author":"K Maharana","year":"2022","unstructured":"Maharana, K., Mondal, S., & Nemade, B. (2022). A review: Data pre-processing and data augmentation techniques. Glob. Transit. Proc.,3(1), 91\u201399.","journal-title":"Glob. Transit. Proc."},{"key":"2656_CR60","first-page":"1","volume":"61","author":"X Ma","year":"2023","unstructured":"Ma, X., Zhang, X., Wang, Z., & Pun, M.-O. (2023). Unsupervised domain adaptation augmented by mutually boosted attention for semantic segmentation of vhr remote sensing images. IEEE Trans. Geosci. Remote. Sens.,61, 1\u201315.","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"2656_CR61","unstructured":"Menon, A.K., Jayasumana, S., Rawat, A.S., Jain, H., Veit, A. & Kumar, S. (2021). Long-tail learning via logit adjustment. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR62","unstructured":"Mirza, M. & Osindero, S. (2014). Conditional generative adversarial nets. In: Proc. Adv. Neural Inf. Process. Syst., pp. 2672\u20132680."},{"key":"2656_CR63","unstructured":"Mishra, S., Murugesan, B., Ayed, I.B. & Pedersoli, M. (2024). Do not trust what you trust: Miscalibration in semi-supervised learning. Transact. Mach. Learn. Res."},{"key":"2656_CR64","doi-asserted-by":"crossref","unstructured":"Moayeri, M., Pope, P., Balaji, Y. & Feizi, S. (2022). A comprehensive study of image classification model sensitivity to foregrounds, backgrounds, and visual attributes. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 19087\u201319097.","DOI":"10.1109\/CVPR52688.2022.01850"},{"key":"2656_CR65","unstructured":"Netzer, Y., & others. (2011). Reading digits in natural images with unsupervised feature learning. In: Workshop of Adv. Neural Inf. Process. Syst., pp. 1\u20139"},{"key":"2656_CR66","doi-asserted-by":"crossref","unstructured":"Ni, J., Li, J. & McAuley, J. (2019). Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In: Proc. Conf. Empir. Methods Natural Lang. Process., pp. 188\u2013197.","DOI":"10.18653\/v1\/D19-1018"},{"key":"2656_CR67","unstructured":"Odena, A., Olah, C. & Shlens, J. (2017). Conditional image synthesis with auxiliary classifier gans. In: Proc. Int. Conf. Mach. Learn., pp. 2642\u20132651."},{"key":"2656_CR68","unstructured":"Reddy, A.G., Bachu, S., Dash, S., Sharma, C., Sharma, A. & Balasubramanian, V.N. (2023). On counterfactual data augmentation under confounding. arXiv preprint arXiv:2305.18183."},{"key":"2656_CR69","unstructured":"Ren, Z., Yeh, R. & Schwing, A. (2020). Not all unlabeled data are equal: Learning to weight data in semi-supervised learning. In: Proc. Adv. Neural Inf. Process. Syst., pp. 21786\u201321797."},{"key":"2656_CR70","unstructured":"Ren, J., Yu, C., Ma, X., Zhao, H., Yi, S. & others. (2020). Balanced meta-softmax for long-tailed visual recognition. In: Proc. Adv. Neural Inf. Process. Syst., pp. 4175\u20134186."},{"key":"2656_CR71","unstructured":"Sagawa, S., Koh, P.W., Hashimoto, T.B. & Liang, P. (2020). Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR72","unstructured":"Sanh, V., Debut, L., Chaumond, J. & Wolf, T. (2019). Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter. In: Workshop of Adv. Neural Inf. Process. Syst."},{"key":"2656_CR73","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D. & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"2656_CR74","unstructured":"Shi, Y., Seely, J., Torr, P. HS., Siddharth, N., Hannun, A., Usunier, N. & Synnaeve, G. (2022). Gradient matching for domain generalization. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR75","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. J. Big Data,6, 1\u201348.","journal-title":"J. Big Data"},{"key":"2656_CR76","unstructured":"Shu, J., Xie, Q., Yi, L., Zhao, Q., Zhou, S., Xu, Z., & Meng, D. (2019). Meta-weight-net: Learning an explicit mapping for sample weighting. In: Proc. Adv. Neural Inf. Process. Syst., pp. 1919\u20131930."},{"key":"2656_CR77","unstructured":"Simonyan, K. & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR78","doi-asserted-by":"crossref","unstructured":"Singla, S., Murali, N., Arabshahi, F., Triantafyllou, S. & Batmanghelich, K. (2023). Augmentation by counterfactual explanation-fixing an overconfident classifier. In: Proc. IEEE Winter Conf. Appl. Comput. Vis., pp. 4720\u20134730.","DOI":"10.1109\/WACV56688.2023.00470"},{"key":"2656_CR79","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.A., Cubuk, E. D., Kurakin, A. & Li, C.-L. (2020). Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In: Proc. Adv. Neural Inf. Process. Syst., pp. 596\u2013608."},{"key":"2656_CR80","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.neunet.2022.12.008","volume":"159","author":"K Suetake","year":"2023","unstructured":"Suetake, K., Ikegawa, S.-I., Saiin, R., & Sawada, Y. (2023). S3nn: Time step reduction of spiking surrogate gradients for training energy efficient single-step spiking neural networks. Neural Netw.,159, 208\u2013219.","journal-title":"Neural Netw."},{"key":"2656_CR81","unstructured":"Tai, K.S., Bailis, P.D. & Valiant, G. (2021). Sinkhorn label allocation: Semi-supervised classification via annealed self-training. In: Proc. Int. Conf. Mach. Learn., pp. 10065\u201310075."},{"key":"2656_CR82","unstructured":"Tang, K., Huang, J. & Zhang, H. (2020). Long-tailed classification by keeping the good and removing the bad momentum causal effect. In: Proc. Adv. Neural Inf. Process. Syst., pp. 1513\u20131524."},{"key":"2656_CR83","doi-asserted-by":"crossref","unstructured":"Tang, K., Tao, M., Qi, J., Liu, Z. & Zhang, H. (2022). Invariant feature learning for generalized long-tailed classification. In: Proc. Eur. Conf. Comput. Vis., pp. 709\u2013726.","DOI":"10.1007\/978-3-031-20053-3_41"},{"key":"2656_CR84","unstructured":"Tarvainen, A. & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: Proc. Adv. Neural Inf. Process. Syst., pp. 1195\u20131204."},{"key":"2656_CR85","unstructured":"Taylor, J., Earnshaw, B., Mabey, B., Victors, M. & Yosinski, J. (2019). Rxrx1: An image set for cellular morphological variation across many experimental batches. In: Workshop of Int. Conf. Learn. Represent."},{"key":"2656_CR86","unstructured":"Toneva, M., Sordoni, A., Combes, R.T., Trischler, A., Bengio, Y. & Gordon, G.J. (2018). An empirical study of example forgetting during deep neural network learning. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR87","unstructured":"Wang, W., Han, C., Zhou, T. & Liu, D. (2023). Visual recognition with deep nearest centroids. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR88","unstructured":"Wang, X., Lian, L., Miao, Z., Liu, Z. & Yu, S. (2020). Long-tailed recognition by routing diverse distribution-aware experts. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR89","unstructured":"Wang, Y., Pan, X., Song, S., Zhang, H., Wu, C. & Huang, G. (2019). Implicit semantic data augmentation for deep networks. In: Proc. Adv. Neural Inf. Process. Syst., pp. 12635\u201312644."},{"key":"2656_CR90","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8113\/41\/6\/065004","volume":"41","author":"QA Wang","year":"2008","unstructured":"Wang, Q. A. (2008). Probability distribution and entropy as a measure of uncertainty. J. Phys. A: Math. Theor.,41, Article 065004.","journal-title":"J. Phys. A: Math. Theor."},{"key":"2656_CR91","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1109\/TIP.2024.3354420","volume":"33","author":"M Wang","year":"2024","unstructured":"Wang, M., Liu, Y., Yuan, J., Wang, S., Wang, Z., & Wang, W. (2024). Inter-class and inter-domain semantic augmentation for domain generalization. IEEE Trans. Image Process.,33, 1338\u20131347.","journal-title":"IEEE Trans. Image Process."},{"key":"2656_CR92","doi-asserted-by":"crossref","unstructured":"Wen, Y., Zhang, K., Li, Z. & Qiao, Y. (2016). A discriminative feature learning approach for deep face recognition. In: Proc. Eur. Conf. Comput. Vis., pp. 499\u2013515.","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"2656_CR93","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn.,8, 229\u2013256.","journal-title":"Mach. Learn."},{"key":"2656_CR94","doi-asserted-by":"crossref","unstructured":"Wu, Z., Arora, A., Wang, Z., Geiger, A., Jurafsky, D., Manning, C.D. & Potts, C. (2024). Reft: Representation finetuning for language models. In: Proc. Adv. Neural Inf. Process. Syst., pp. 63908\u201363962.","DOI":"10.52202\/079017-2041"},{"key":"2656_CR95","doi-asserted-by":"crossref","unstructured":"Wu, M., Liu, W., Wang, X., Li, T., Lv, C., Ling, Z., Zhu, J., Zhang, C., Zheng, X. & Huang, X. (2024). Advancing parameter efficiency in fine-tuning via representation editing. In: Proc. Annu. Meet. Assoc. Comput Linguist., pp. 13445\u201313464.","DOI":"10.18653\/v1\/2024.acl-long.726"},{"key":"2656_CR96","unstructured":"Wu, D., Wen, L., Chen, C. & Shi, Z. (2024). A novel counterfactual data augmentation method for aspect-based sentiment analysis. In: Proc. Asian Conf. Mach. Learn., pp. 1479\u20131493."},{"key":"2656_CR97","unstructured":"Wu, S., Yuksekgonul, M., Zhang, L. & Zou, J. (2023). Discover and cure: Concept-aware mitigation of spurious correlation. In: Proc. Int. Conf. Mach. Learn., pp. 37765\u201337786."},{"key":"2656_CR98","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Tang, Z., Wei, P., Liu, C. & Lin, L. (2023). Masked images are counterfactual samples for robust fine-tuning. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 20301\u201320310.","DOI":"10.1109\/CVPR52729.2023.01944"},{"key":"2656_CR99","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, T. & Le, Q. (2020). Unsupervised data augmentation for consistency training. In: Proc. Adv. Neural Inf. Process. Syst., pp. 6256\u20136268."},{"key":"2656_CR100","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z. & He, K. (2017). Aggregated residual transformations for deep neural networks. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 5987\u20135995.","DOI":"10.1109\/CVPR.2017.634"},{"key":"2656_CR101","doi-asserted-by":"crossref","unstructured":"Xie, L., Wang, J., Wei, Z., Wang, M. & Tian, Q. (2016). Disturblabel: Regularizing cnn on the loss layer. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 4753\u20134762.","DOI":"10.1109\/CVPR.2016.514"},{"issue":"4","key":"2656_CR102","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1007\/s11263-023-01944-1","volume":"132","author":"M Xie","year":"2024","unstructured":"Xie, M., Li, S., Gong, K., Wang, Y., & Huang, G. (2024). Adapting across domains via target-oriented transferable semantic augmentation under prototype constraint. Int. J. Comput. Vision,132(4), 1417\u20131441.","journal-title":"Int. J. Comput. Vision"},{"key":"2656_CR103","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Hu, H., Wang, J., Wang, L., Wei, F., Bai, X. & Liu, Z. (2021). End-to-end semi-supervised object detection with soft teacher. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 3060\u20133069.","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"2656_CR104","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, J., Ni, B., Li, T., Wang, C., Tian, Q. & Zhang, W. (2020). Adversarial domain adaptation with domain mixup. In: Proc. AAAI Conf. Artif. Intell., pp. 6502\u20136509.","DOI":"10.1609\/aaai.v34i04.6123"},{"issue":"8","key":"2656_CR105","doi-asserted-by":"publisher","first-page":"3208","DOI":"10.1007\/s11263-024-02015-9","volume":"132","author":"Z Yang","year":"2024","unstructured":"Yang, Z., Yue, J., Ghamisi, P., Zhang, S., Ma, J., & Fang, L. (2024). Open set recognition in real world. Int. J. Comput. Vision,132(8), 3208\u20133231.","journal-title":"Int. J. Comput. Vision"},{"key":"2656_CR106","unstructured":"Yao, H., Wang, Y., Li, S., Zhang, L., Liang, W., Zou, J. & Finn, C. (2022). Improving out-of-distribution robustness via selective augmentation. In: Proc. Int. Conf. Mach. Learn., pp. 25407\u201325437."},{"key":"2656_CR107","doi-asserted-by":"crossref","unstructured":"Young, K., Booth, G., Simpson, B., Dutton, R. & Shrapnel, S. (2019). Deep neural network or dermatologist? In: Proc. Interpret. Mach. Intell. Med. Image Comput., pp. 48\u201355.","DOI":"10.1007\/978-3-030-33850-3_6"},{"key":"2656_CR108","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S. & Komodakis, N. (2016). Wide residual networks. In: Proc. Brit. Mach. Vis. Conf.","DOI":"10.5244\/C.30.87"},{"key":"2656_CR109","unstructured":"Zhang, Z. & Sabuncu, M.R. (2018). Generalized cross entropy loss for training deep neural networks with noisy labels. In: Proc. Adv. Neural Inf. Process. Syst., pp. 8792\u20138802."},{"key":"2656_CR110","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., & Lopez-Paz, D. (2018). Mixup: Beyond empirical risk minimization. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR111","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Feng, M., Li, Z. & Xu, C. (2024). Discover and mitigate multiple biased subgroups in image classifiers. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 10906\u201310915.","DOI":"10.1109\/CVPR52733.2024.01037"},{"key":"2656_CR112","unstructured":"Zhang, Y., Hooi, B., Hong, L. & Feng, J. (2021). Test-agnostic long-tailed recognition by test-time aggregating diverse experts with self-supervision. arXiv preprint arXiv:2107.09249"},{"key":"2656_CR113","unstructured":"Zhang, M., Sohoni, N.S., Zhang, H.R., Finn, C. & Re, C. (2022). Correct-n-contrast: A contrastive approach for improving robustness to spurious correlations. In: Proc. Int. Conf. Mach. Learn., pp. 26484\u201326516."},{"key":"2656_CR114","unstructured":"Zhang, B., Wang, Y., Hou, W., Wu, H., Wang, J., Okumura, M. & Shinozaki, T. (2021). Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. In: Proc. Adv. Neural Inf. Process. Syst., pp. 18408\u201318419."},{"key":"2656_CR115","unstructured":"Zhang, J., Zhu, J., Niu, G., Han, B., Sugiyama, M. & Kankanhalli, M. (2021). Geometry-aware instance-reweighted adversarial training. In: Proc. Int. Conf. Learn. Represent."},{"key":"2656_CR116","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2023.01.063","volume":"527","author":"S Zhang","year":"2023","unstructured":"Zhang, S., Chen, C., Hu, X., & Peng, S. (2023). Balanced knowledge distillation for long-tailed learning. Neurocomputing,527, 36\u201346.","journal-title":"Neurocomputing"},{"key":"2656_CR117","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Chen, W., Tan, X., Huang, K. & Zhu, J. (2022). Adaptive logit adjustment loss for long-tailed visual recognition. In: Proc. AAAI Conf. Artif. Intell., pp. 3472\u20133480.","DOI":"10.1609\/aaai.v36i3.20258"},{"key":"2656_CR118","doi-asserted-by":"crossref","unstructured":"Zhao, G., Li, G., Qin, Y., Zhang, J., Chai, Z., Wei, X., Lin, L., & Yu, Y. (2024). Exploration and exploitation of unlabeled data for open-set semi-supervised learning. Int. J. Comput. Vision,132(12), 5888\u20135904.","DOI":"10.1007\/s11263-024-02155-y"},{"key":"2656_CR119","doi-asserted-by":"crossref","unstructured":"Zheng, M., You, S., Huang, L., Wang, F., Qian, C. & Xu, C. (2022). Simmatch: Semi-supervised learning with similarity matching. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 14471\u201314481.","DOI":"10.1109\/CVPR52688.2022.01407"},{"key":"2656_CR120","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Cui, J., Liu, S. & Jia, J. (2021). Improving calibration for long-tailed recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 16489\u201316498.","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"2656_CR121","doi-asserted-by":"crossref","unstructured":"Zhou, B., Cui, Q., Wei, X.-S. & Chen, Z.-M. (2020). Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 9719\u20139728.","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"2656_CR122","unstructured":"Zhou, T., Wang, S. & Bilmes, J. (2020). Time-consistent self-supervision for semi-supervised learning. In: Proc. Int. Conf. Mach. Learn., pp. 11523\u201311533"},{"key":"2656_CR123","unstructured":"Zhou, X., Wu, O. & Ng, M.K (2023). Implicit counterfactual data augmentation for deep neural networks. arXiv preprint arXiv:2304.13431."},{"key":"2656_CR124","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yang, N. & Wu, O. (2023). Combining adversaries with anti-adversaries in training. In: Proc. AAAI Conf. Artif. Intell., pp. 11435\u201311442.","DOI":"10.1609\/aaai.v37i9.26352"},{"key":"2656_CR125","unstructured":"Zhou, X., Ye, W., Lee, Z., Xie, R. & Zhang, S. (2024). Boosting model resilience via implicit adversarial data augmentation. In: Int. Joint Conf. Artif. Intell., pp. 5653\u20135661."},{"key":"2656_CR126","unstructured":"Zhou, X., Ye, W., Lee, Z., Xie, R. & Zhang, S. (2024). Boosting model resilience via implicit adversarial data augmentation. In: Proc. Int. Joint Conf. Artif. Intell., pp. 5653\u20135661."},{"issue":"9","key":"2656_CR127","doi-asserted-by":"publisher","first-page":"2377","DOI":"10.1007\/s11263-023-01821-x","volume":"131","author":"K Zhou","year":"2023","unstructured":"Zhou, K., Loy, C. C., & Liu, Z. (2023). Semi-supervised domain generalization with stochastic stylematch. Int. J. Comput. Vision,131(9), 2377\u20132387.","journal-title":"Int. J. Comput. Vision"},{"issue":"9","key":"2656_CR128","doi-asserted-by":"publisher","first-page":"3375","DOI":"10.1007\/s11263-024-02036-4","volume":"132","author":"L Zhu","year":"2024","unstructured":"Zhu, L., Yin, W., Yang, Y., Wu, F., Zeng, Z., Gu, Q., Wang, X., Zhou, C., & Ye, N. (2024). Vision-language alignment learning under affinity and divergence principles for few-shot out-of-distribution generalization. Int. J. Comput. Vision,132(9), 3375\u20133407.","journal-title":"Int. J. Comput. Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02656-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02656-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02656-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T15:21:27Z","timestamp":1771341687000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02656-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":128,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2656"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02656-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]},"assertion":[{"value":"4 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Our code is available at\n                      \n                      .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code Availability"}}],"article-number":"64"}}