{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T20:29:02Z","timestamp":1786998542659,"version":"build-2736575974"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Research Projects of Ordinary Universities in Guangdong Province","award":["2023KTSCX133"],"award-info":[{"award-number":["2023KTSCX133"]}]},{"name":"The Guangdong Ordinary University Key Laboratory","award":["2021KSYS008"],"award-info":[{"award-number":["2021KSYS008"]}]},{"name":"The Guangdong Basic and Applied Basic Research Foundation","award":["2022A1515140103"],"award-info":[{"award-number":["2022A1515140103"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s11760-026-05638-2","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T21:47:11Z","timestamp":1786484831000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Balancing clean accuracy and gradient robustness via mask-guided mixup and adaptive label refinement"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1552-7310","authenticated-orcid":false,"given":"Guo","family":"Niu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6802-5521","authenticated-orcid":false,"given":"Huanlin","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0089-2651","authenticated-orcid":false,"given":"Shengjun","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8464-8448","authenticated-orcid":false,"given":"Xiongfei","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1348-2060","authenticated-orcid":false,"given":"Tao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3805-3237","authenticated-orcid":false,"given":"Shuaiwei","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4038-3053","authenticated-orcid":false,"given":"Nannan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"5638_CR1","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":"5638_CR2","unstructured":"Zhang, H., Yu, Y., Jiao, J., Xing, E.P., El\u00a0Ghaoui, L., Jordan, M.I.: Theoretically principled trade-off between robustness and accuracy. In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 7472\u20137482 (2019). PMLR"},{"key":"5638_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121361","volume":"237","author":"T Xie","year":"2024","unstructured":"Xie, T., Dai, K., Wang, K., Li, R., Zhao, L.: Deepmatcher: a deep transformer-based network for robust and accurate local feature matching. Expert Syst. Appl. 237, 121361 (2024)","journal-title":"Expert Syst. Appl."},{"key":"5638_CR4","unstructured":"Rice, L., Wong, E., Kolter, J.Z.: Overfitting in adversarially robust deep learning. In: Proceedings of the 37th International Conference on Machine Learning (ICML), pp. 8093\u20138104. (2020). (PMLR)"},{"key":"5638_CR5","doi-asserted-by":"crossref","unstructured":"Pan, C., Li, Q., Yao, X.: Adversarial initialization with universal adversarial perturbation: A new approach to fast adversarial training. In: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), pp. 21501\u201321509. (2024)","DOI":"10.1609\/aaai.v38i19.30147"},{"key":"5638_CR6","unstructured":"Verma, V., Lamb, A., Beckham, C., Najafi, A., Mitliagkas, I., Lopez-Paz, D., Bengio, Y.: Manifold mixup: Better representations by interpolating hidden states. In: PMLR Proceedings of the 36th International Conference on Machine Learning, pp. 6438\u20136447. (2019)"},{"key":"5638_CR7","unstructured":"Zhang, H., Wang, J.: Defense against adversarial attacks using feature scattering-based adversarial training. In: Advances in Neural Information Processing Systems (2019)"},{"key":"5638_CR8","unstructured":"Cohen, J., Rosenfeld, E., Kolter, Z.: Certified adversarial robustness via randomized smoothing. In: Proceedings of the 36th International Conference on Machine Learning, pp. 1310\u20131320. (2019). (PMLR)"},{"key":"5638_CR9","first-page":"58023","volume":"36","author":"N Tsilivis","year":"2023","unstructured":"Tsilivis, N., Frank, N., Srebro, N., Kempe, J.: The price of implicit bias in adversarially robust generalization. Adv. Neural Inf. Process. Syst. (NeurIPS) 36, 58023\u201358057 (2023)","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"5638_CR10","doi-asserted-by":"crossref","unstructured":"Li, Z., Yu, D., Wei, L., Jin, C., Zhang, Y., Chan, S.: Soften to defend: Towards adversarial robustness via self-guided label refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24776\u201324785 (2024)","DOI":"10.1109\/CVPR52733.2024.02340"},{"key":"5638_CR11","doi-asserted-by":"crossref","unstructured":"Song, K., Lai, H., Pan, Y., Yin, J.: Mimicdiffusion: Purifying adversarial perturbation via mimicking clean diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24665\u201324674 (2024)","DOI":"10.1109\/CVPR52733.2024.02329"},{"key":"5638_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, W.-D., Chang, C.-Y., Huang, T.-C., Lee, Y.-S.: An explainable kan-shapley framework for many-to-many electric vehicle charging dispatch in intelligent transportation systems. In: IEEE Trans. Intell. Transp. Syst. (2026)","DOI":"10.1109\/TITS.2026.3688187"},{"issue":"4","key":"5638_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2025.104153","volume":"62","author":"W-D Jiang","year":"2025","unstructured":"Jiang, W.-D., Chang, C.-Y., Yen, S.-J., Wu, S.-J., Roy, D.S.: Realexp: Decoupling correlation bias in shapley values for faithful model interpretations. Inf. Process. Manag. 62(4), 104153 (2025)","journal-title":"Inf. Process. Manag."},{"key":"5638_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126720","volume":"272","author":"Y-S Lee","year":"2025","unstructured":"Lee, Y.-S., Yen, S.-J., Jiang, W., Chen, J., Chang, C.-Y.: Illuminating the black box: an interpretable machine learning based on ensemble trees. Expert Syst. Appl. 272, 126720 (2025)","journal-title":"Expert Syst. Appl."},{"key":"5638_CR15","first-page":"18","volume":"1","author":"W-D Jiang","year":"2026","unstructured":"Jiang, W.-D., Chang, C.-Y., Huang, T.-C., Chin, Y.-T., Roy, D.S.: PEXP: a scalable parallel tree-based framework for interpreting models on big data. IEEE Trans. Big Data 1, 18 (2026)","journal-title":"IEEE Trans. Big Data"},{"key":"5638_CR16","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"5638_CR17","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"5638_CR18","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.1609\/aaai.v33i01.33013714","volume":"33","author":"H Guo","year":"2019","unstructured":"Guo, H., Mao, Y., Zhang, R.: Mixup as locally linear out-of-manifold regularization. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI) 33, 3714\u20133722 (2019)","journal-title":"Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"5638_CR19","doi-asserted-by":"crossref","unstructured":"Thulasidasan, S., Chennupati, G., Bilmes, J.A., Bhattacharya, T., Michalak, S.: On mixup training: improved calibration and predictive uncertainty. In: Advances in Neural Information Processing Systems (2019)","DOI":"10.2172\/1525811"},{"key":"5638_CR20","unstructured":"Choi, J.-H., Kim, D., Yoon, K.-J.: Tokenmix: Rethinking mixup for transformers. In: European Conference on Computer Vision (ECCV) (2022)"},{"key":"5638_CR21","doi-asserted-by":"crossref","unstructured":"Chen, J.-N., Sun, S., He, J., Torr, P.H., Yuille, A., Bai, S.: Transmix: Attend to mix for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12135\u201312144 (2022)","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"5638_CR22","unstructured":"Uddin, A.F.M.S., Monira, M.S., Shin, W., Chung, T., Bae, S.-H.: Saliencymix: A saliency guided data augmentation strategy for better regularization. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"5638_CR23","unstructured":"Wang, Y., Zhang, Y., Jiao, J., Xu, D., Wornell, G., El Ghaoui, L., Jordan, M.I.: The geometry of adversarial training: a manifold perspective. In: International Conference on Machine Learning (ICML), pp. 36257\u201336277 (2023)"},{"key":"5638_CR24","unstructured":"Moosavi-Dezfooli, S.-M., Fawzi, A., Frossard, P.: Understanding the geometry of adversarial examples. IEEE Trans. Pattern Anal. Mach. Intell. (2022) TPAMI"},{"key":"5638_CR25","unstructured":"Kim, J.-H., Choo, W., Song, H.O.: Puzzle mix: Exploiting saliency and local statistics for optimal mixup. In: International Conference on Machine Learning, pp. 5275\u20135285 (2020). (PMLR)"},{"key":"5638_CR26","doi-asserted-by":"crossref","unstructured":"Walawalkar, D., Shen, Z., Liu, Z., Savvides, M.: Attentive cutmix: an enhanced data augmentation approach for deep learning based image classification. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3642\u20133646 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053994"},{"key":"5638_CR27","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 1195\u20131204 (2017)"},{"key":"5638_CR28","doi-asserted-by":"crossref","unstructured":"Na, J., Ha, J.W., Chang, H., Han, D., Hwang, W.: Switching temporary teachers for semi-supervised semantic segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)","DOI":"10.52202\/075280-1754"},{"key":"5638_CR29","unstructured":"Li, S.: Switch ema: A free lunch for better flatness and sharpness (2024). arXiv:2402.09240 arXiv preprint"},{"key":"5638_CR30","unstructured":"Xu, M., Lee, J., Yoon, S., Park, D.S.: Adaptive label smoothing for out-of-distribution detection (2024). arXiv:2410.06134 arXiv preprint"},{"key":"5638_CR31","unstructured":"Morales-Brotons, D., Vogels, T., Hendrikx, H.: Exponential moving average of weights in deep learning: Dynamics and benefits. In: Transactions on Machine Learning Research (2024)"},{"key":"5638_CR32","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.,: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, p. 4 (2011)"},{"key":"5638_CR33","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images, University of Toronto (2009). (Technical report)"},{"key":"5638_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5638_CR35","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss landscape of neural nets. In: NeurIPS (2018)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05638-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05638-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05638-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:27:40Z","timestamp":1786994860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05638-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":35,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["5638"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05638-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"7 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that generative artificial intelligence tools were used solely for language polishing and clarity improvement during the preparation of this manuscript.","order":2,"name":"Ethics","label":"AI use","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors have read and agreed to the published version of the manuscript.","order":3,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"570"}}