{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:16:16Z","timestamp":1778692576236,"version":"3.51.4"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"China\u2019s Key Research and Development Program","award":["2024YFE0198300"],"award-info":[{"award-number":["2024YFE0198300"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s10994-026-07035-9","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T11:28:59Z","timestamp":1775215739000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MultiScale Knowledge Distillation"],"prefix":"10.1007","volume":"115","author":[{"given":"Siyuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zikang","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"key":"7035_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, S., Hu, S.X., Damianou, A., Lawrence, N.D., & Dai, Z.(2019). Variational information distillation for knowledge transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9163\u20139171","DOI":"10.1109\/CVPR.2019.00938"},{"key":"7035_CR2","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., & Weston, J.(2009). Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41\u201348","DOI":"10.1145\/1553374.1553380"},{"key":"7035_CR3","doi-asserted-by":"publisher","unstructured":"Chen, W.-C., & Chu, W.-T. (2023). Sssd: Self-supervised self distillation. In: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2769\u20132776 . https:\/\/doi.org\/10.1109\/WACV56688.2023.00279","DOI":"10.1109\/WACV56688.2023.00279"},{"key":"7035_CR4","doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, S., Zhao, H., & Jia, J.(2021). Distilling knowledge via knowledge review. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5008\u20135017","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"7035_CR5","doi-asserted-by":"publisher","unstructured":"Chen, D., Mei, J.-P., Zhang, H., Wang, C., Feng, Y., & Chen, C. (2022). Knowledge distillation with the reused teacher classifier. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11923\u201311932 . https:\/\/doi.org\/10.1109\/CVPR52688.2022.01163","DOI":"10.1109\/CVPR52688.2022.01163"},{"key":"7035_CR6","doi-asserted-by":"crossref","unstructured":"Chen, D., Mei, J.-P., Zhang, H., Wang, C., Feng, Y.,& Chen, C.(2022). Knowledge distillation with the reused teacher classifier. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11933\u201311942","DOI":"10.1109\/CVPR52688.2022.01163"},{"key":"7035_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zheng, X., Shen, H., Zeng, Z., Zhou, Y., & Zhao, R.(2020). Improving knowledge distillation via category structure. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXVIII 16, pp. 205\u2013219 . Springer","DOI":"10.1007\/978-3-030-58604-1_13"},{"key":"7035_CR8","doi-asserted-by":"crossref","unstructured":"Cho, J.H., & Hariharan, B.(2019). On the efficacy of knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4794\u20134802","DOI":"10.1109\/ICCV.2019.00489"},{"key":"7035_CR9","unstructured":"Coates, A., Ng, A., & Lee, H. (2011). An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223 . JMLR Workshop and Conference Proceedings"},{"key":"7035_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L.(2009). Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 . Ieee","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"5","key":"7035_CR11","doi-asserted-by":"publisher","first-page":"3233","DOI":"10.1007\/s10994-021-05948-1","volume":"113","author":"R Eyraud","year":"2024","unstructured":"Eyraud, R., & Ayache, S. (2024). Distillation of weighted automata from recurrent neural networks using a spectral approach. Machine Learning, 113(5), 3233\u20133266. https:\/\/doi.org\/10.1007\/s10994-021-05948-1","journal-title":"Machine Learning"},{"issue":"10","key":"7035_CR12","doi-asserted-by":"publisher","first-page":"8137","DOI":"10.1007\/s10994-024-06524-z","volume":"113","author":"K Faber","year":"2024","unstructured":"Faber, K., Zurek, D., Pietron, M., Japkowicz, N., Vergari, A., & Corizzo, R. (2024). From mnist to imagenet and back: benchmarking continual curriculum learning. Machine Learning, 113(10), 8137\u20138164. https:\/\/doi.org\/10.1007\/s10994-024-06524-z","journal-title":"Machine Learning"},{"issue":"6","key":"7035_CR13","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129(6), 1789\u20131819.","journal-title":"International Journal of Computer Vision"},{"key":"7035_CR14","doi-asserted-by":"crossref","unstructured":"Guo, Z., Yan, H., Li, H., & Lin, X.(2023). Class attention transfer based knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11868\u201311877","DOI":"10.1109\/CVPR52729.2023.01142"},{"key":"7035_CR15","doi-asserted-by":"crossref","unstructured":"Han, D., Kim, J., & Kim, J. (2017). Deep pyramidal residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5927\u20135935","DOI":"10.1109\/CVPR.2017.668"},{"key":"7035_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J.(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":"7035_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S.,& Sun, J.(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":"7035_CR18","doi-asserted-by":"crossref","unstructured":"Heo, B., Kim, J., Yun, S., Park, H., Kwak, N.,& Choi, J.Y.(2019). A comprehensive overhaul of feature distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1921\u20131930","DOI":"10.1109\/ICCV.2019.00201"},{"key":"7035_CR19","unstructured":"Hinton, G.(2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531"},{"key":"7035_CR20","unstructured":"Hossain, M.I., Akhter, S., Hong, C.S., & Huh, E.-N.(2025). Single teacher, multiple perspectives: Teacher knowledge augmentation for enhanced knowledge distillation. In: Yue, Y., Garg, A., Peng, N., Sha, F., Yu, R. (eds.) International Conference on Learning Representations, vol. 2025, pp. 91583\u201391594"},{"key":"7035_CR21","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., & Weinberger, K.Q.(2017). Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"7035_CR22","doi-asserted-by":"crossref","unstructured":"Huang, T., You, S., Wang, F., Qian, C., & Xu, C.(2022). Knowledge distillation from a stronger teacher. ArXiv abs\/2205.10536","DOI":"10.52202\/068431-2443"},{"key":"7035_CR23","doi-asserted-by":"crossref","unstructured":"Jin, Y., Wang, J., & Lin, D.(2023). Multi-level logit distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24276\u201324285","DOI":"10.1109\/CVPR52729.2023.02325"},{"key":"7035_CR24","unstructured":"Joshi, C.K., Liu, F., Xun, X., Lin, J., & Foo, C.S.(2022). On representation knowledge distillation for graph neural networks. IEEE transactions on neural networks and learning systems"},{"key":"7035_CR25","unstructured":"Krizhevsky, A., Hinton, G., and others.(2009). Learning multiple layers of features from tiny images"},{"key":"7035_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Guo, Z., Li, H., Han, S., Baek, J.-W., Yang, M., Yang, R., & Suh, S.(2023). Rethinking feature-based knowledge distillation for face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20156\u201320165","DOI":"10.1109\/CVPR52729.2023.01930"},{"key":"7035_CR27","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, X., Yang, L., Zhao, B., Song, R., Luo, L., Li, J., & Yang, J.(2023). Curriculum temperature for knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 1504\u20131512","DOI":"10.1609\/aaai.v37i2.25236"},{"issue":"6","key":"7035_CR28","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1631\/FITEE.2400383","volume":"26","author":"D Li","year":"2025","unstructured":"Li, D., Li, P., Wu, A., & Han, Y. (2025). Prototype-guided cross-task knowledge distillation. Frontiers of Information Technology & Electronic Engineering, 26(6), 912\u2013929. https:\/\/doi.org\/10.1631\/FITEE.2400383","journal-title":"Frontiers of Information Technology & Electronic Engineering"},{"key":"7035_CR29","doi-asserted-by":"publisher","unstructured":"Liu, J., Li, B., Lei, M., & Shi, Y. (2022). Self-supervised knowledge distillation for complementary label learning. Neural Networks,155, 318\u2013327. https:\/\/doi.org\/10.1016\/j.neunet.2022.08.014","DOI":"10.1016\/j.neunet.2022.08.014"},{"key":"7035_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119202","volume":"642","author":"J Li","year":"2023","unstructured":"Li, J., Zhou, S., Li, L., Wang, H., Bu, J., & Yu, Z. (2023). Dynamic data-free knowledge distillation by easy-to-hard learning strategy. Information Sciences, 642, Article 119202.","journal-title":"Information Sciences"},{"key":"7035_CR31","doi-asserted-by":"publisher","unstructured":"Lu, G., Yin, H., Shu, Z., Wang, J., & Luo, G.(2025). Bdckd: Unlocking the power of brownian distance covariance in knowledge distillation. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 . https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10889695","DOI":"10.1109\/ICASSP49660.2025.10889695"},{"key":"7035_CR32","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., & Sun, J.(2018). Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"7035_CR33","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S.I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A.,& Ghasemzadeh, H.(2020). Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5191\u20135198","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"7035_CR34","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., & Cho, M.(2019). Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3967\u20133976","DOI":"10.1109\/CVPR.2019.00409"},{"issue":"5","key":"7035_CR35","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.1109\/TNNLS.2020.2995884","volume":"32","author":"N Passalis","year":"2020","unstructured":"Passalis, N., Tzelepi, M., & Tefas, A. (2020). Probabilistic knowledge transfer for lightweight deep representation learning. IEEE Transactions on Neural Networks and learning systems, 32(5), 2030\u20132039.","journal-title":"IEEE Transactions on Neural Networks and learning systems"},{"key":"7035_CR36","doi-asserted-by":"crossref","unstructured":"Peng, B., Jin, X., Liu, J., Li, D., Wu, Y., Liu, Y., Zhou, S., & Zhang, Z.(2019). Correlation congruence for knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5007\u20135016","DOI":"10.1109\/ICCV.2019.00511"},{"key":"7035_CR37","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., & Bengio, Y.(2014). Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550"},{"key":"7035_CR38","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., & Bengio, Y.(2014). Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550"},{"key":"7035_CR39","doi-asserted-by":"crossref","unstructured":"Song, K., Xie, J., Zhang, S., & Luo, Z.(2023). Multi-mode online knowledge distillation for self-supervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11848\u201311857","DOI":"10.1109\/CVPR52729.2023.01140"},{"key":"7035_CR40","doi-asserted-by":"crossref","unstructured":"Sun, S., Ren, W., Li, J., Wang, R.,& Cao, X.(2024). Logit standardization in knowledge distillation. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 15731\u201315740","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"7035_CR41","unstructured":"Tian, Y., Krishnan, D., & Isola, P.(2019). Contrastive representation distillation. arXiv preprint arXiv:1910.10699"},{"issue":"6","key":"7035_CR42","doi-asserted-by":"publisher","first-page":"6305","DOI":"10.1109\/TKDE.2022.3171571","volume":"35","author":"C Wang","year":"2023","unstructured":"Wang, C., Chen, D., Mei, J.-P., Zhang, Y., Feng, Y., & Chen, C. (2023). Semckd: Semantic calibration for cross-layer knowledge distillation. IEEE Transactions on Knowledge and Data Engineering, 35(6), 6305\u20136319. https:\/\/doi.org\/10.1109\/TKDE.2022.3171571","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"3","key":"7035_CR43","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/s10994-024-06657-1","volume":"114","author":"Q Wang","year":"2025","unstructured":"Wang, Q., Qian, X., Li, B., & Xue, X. (2025). Distribution aligned semantics adaption for lifelong person re-identification. Machine Learning, 114(3), 70. https:\/\/doi.org\/10.1007\/s10994-024-06657-1","journal-title":"Machine Learning"},{"key":"7035_CR44","doi-asserted-by":"crossref","unstructured":"Wei, S., Luo, C., & Luo, Y.(2024). Scaled decoupled distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15975\u201315983","DOI":"10.1109\/CVPR52733.2024.01512"},{"key":"7035_CR45","doi-asserted-by":"publisher","first-page":"1516","DOI":"10.1109\/TMM.2023.3282874","volume":"26","author":"S Wei","year":"2023","unstructured":"Wei, S., Luo, C., Luo, Y., & Xu, J. (2023). Privileged modality learning via multimodal hallucination. IEEE Transactions on Multimedia, 26, 1516\u20131527.","journal-title":"IEEE Transactions on Multimedia"},{"key":"7035_CR46","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.-T., Hovy, E., & Le, Q.V.(2020). Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"7035_CR47","doi-asserted-by":"crossref","unstructured":"Xu, G., Liu, Z., Li, X., & Loy, C. C. (2020). Knowledge distillation meets self-supervision. In A. Vedaldi, H. Bischof, T. Brox, & J.-M. Frahm (Eds.), Computer Vision - ECCV 2020 (pp. 588\u2013604). Cham: Springer.","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"7035_CR48","doi-asserted-by":"crossref","unstructured":"Yang, C., An, Z., Cai, L., & Xu, Y.(2021). Hierarchical self-supervised augmented knowledge distillation. ArXiv abs\/2107.13715","DOI":"10.24963\/ijcai.2021\/168"},{"issue":"8","key":"7035_CR49","doi-asserted-by":"publisher","first-page":"10212","DOI":"10.1109\/TPAMI.2023.3257878","volume":"45","author":"C Yang","year":"2023","unstructured":"Yang, C., An, Z., Zhou, H., Zhuang, F., Xu, Y., & Zhang, Q. (2023). Online knowledge distillation via mutual contrastive learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 10212\u201310227.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"7035_CR50","doi-asserted-by":"publisher","first-page":"4188","DOI":"10.1109\/TPAMI.2024.3354928","volume":"46","author":"S Yang","year":"2024","unstructured":"Yang, S., Yang, J., Zhou, M., Huang, Z., Zheng, W.-S., Yang, X., & Ren, J. (2024). Learning from human educational wisdom: A student-centered knowledge distillation method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(6), 4188\u20134205.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"7035_CR51","doi-asserted-by":"publisher","first-page":"1817","DOI":"10.1109\/TPAMI.2022.3160328","volume":"45","author":"H-J Ye","year":"2022","unstructured":"Ye, H.-J., Lu, S., & Zhan, D.-C. (2022). Generalized knowledge distillation via relationship matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), 1817\u20131834.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"7035_CR52","doi-asserted-by":"crossref","unstructured":"You, S., Xu, C., Xu, C., & Tao, D.(2017). Learning from multiple teacher networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1285\u20131294","DOI":"10.1145\/3097983.3098135"},{"key":"7035_CR53","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S.(2016). Wide residual networks. arXiv preprint arXiv:1605.07146","DOI":"10.5244\/C.30.87"},{"key":"7035_CR54","unstructured":"Zagoruyko, S., & Komodakis, N.(2016). Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928"},{"key":"7035_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, C., Liu, J., Dang, K., & Zhang, W.(2022). Multi-scale distillation from multiple graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 4337\u20134344","DOI":"10.1609\/aaai.v36i4.20354"},{"key":"7035_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., & Sun, J.(2018). Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"7035_CR57","unstructured":"Zhao, K., & Zhao, M.(2024). Self-supervised quantization-aware knowledge distillation. In: Dasgupta, S., Mandt, S., Li, Y. (eds.) Proceedings of The 27th International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 238, pp. 4375\u20134383"},{"key":"7035_CR58","doi-asserted-by":"publisher","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., & Liang, J.(2022). Decoupled knowledge distillation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11943\u201311952 . https:\/\/doi.org\/10.1109\/CVPR52688.2022.01165","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"7035_CR59","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., & Liang, J.(2022). Decoupled knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11953\u201311962","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"7035_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107519","volume":"233","author":"H Zhao","year":"2021","unstructured":"Zhao, H., Sun, X., Dong, J., Dong, Z., & Li, Q. (2021). Knowledge distillation via instance-level sequence learning. Knowledge-Based Systems, 233, Article 107519.","journal-title":"Knowledge-Based Systems"},{"key":"7035_CR61","unstructured":"Zheng, K., & YANG, E.-H.(2024). Knowledge distillation based on transformed teacher matching. In: Kim, B., Yue, Y., Chaudhuri, S., Fragkiadaki, K., Khan, M., Sun, Y. (eds.) International Conference on Learning Representations, vol. 2024, pp. 44963\u201344979"},{"issue":"10","key":"7035_CR62","doi-asserted-by":"publisher","first-page":"7645","DOI":"10.1007\/s10994-024-06597-w","volume":"113","author":"Y Zhou","year":"2024","unstructured":"Zhou, Y., Xu, P., & Hooker, G. (2024). A generic approach for reproducible model distillation. Machine Learning, 113(10), 7645\u20137688. https:\/\/doi.org\/10.1007\/s10994-024-06597-w","journal-title":"Machine Learning"},{"key":"7035_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, J., Tang, S., Chen, D., Yu, S., Liu, Y., Rong, M., Yang, A., & Wang, X.(2021). Complementary relation contrastive distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9260\u20139269","DOI":"10.1109\/CVPR46437.2021.00914"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-026-07035-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-026-07035-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-026-07035-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T16:30:29Z","timestamp":1778689829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-026-07035-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":63,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["7035"],"URL":"https:\/\/doi.org\/10.1007\/s10994-026-07035-9","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"9 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2026","order":4,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"91"}}