{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T06:04:28Z","timestamp":1785305068085,"version":"3.55.0"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100018694","name":"HORIZON EUROPE Marie Sklodowska-Curie Actions","doi-asserted-by":"publisher","award":["101154277"],"award-info":[{"award-number":["101154277"]}],"id":[{"id":"10.13039\/100018694","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202137"],"award-info":[{"award-number":["62202137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LMS25F020009"],"award-info":[{"award-number":["LMS25F020009"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tianjin Natural Science Foundation Project","award":["25JCQNJC00740"],"award-info":[{"award-number":["25JCQNJC00740"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Existing knowledge distillation methods indiscriminately transfer knowledge from teacher networks, including output-level decisional biases, i.e., incorrect final predictions that can mislead student learning and limit student performance. We challenge this paradigm by proposing BTKD++, a framework that systematically filters and rectifies teacher\u2019s output-level biased knowledge into corrective signals. Our approach partitions training data into Easy Tasks (correct teacher predictions) and Hard Tasks (incorrect predictions), then applies bias elimination and rectification modules orchestrated by dynamic learning curriculum. We provide an interpretive information-theoretic abstraction to explain the observed competence-threshold phenomenon, under which bias rectification becomes more effective when teacher errors contain sufficiently structured corrective information. BTKD++ demonstrates broad applicability across classification, detection, and segmentation tasks when task outputs are equipped with suitable probabilistic interfaces, and shows consistent effectiveness across CNNs, Transformers, and State-Space Models. Extensive experiments show consistent student-teacher transcendence, establishing new state-of-the-art results. This work redefines knowledge distillation from blind mimicry to critical learning, proving that students can surpass teachers through principled bias correction. The source code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/smartyige\/BTKD\" ext-link-type=\"uri\">https:\/\/github.com\/smartyige\/BTKD<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1007\/s11263-026-02924-x","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T06:36:52Z","timestamp":1783492612000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BTKD++: Beyond Teachers by Critically Distilling Knowledge from Teacher\u2019s Bias"],"prefix":"10.1007","volume":"134","author":[{"given":"Jianhua","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiufeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengyong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2130-9122","authenticated-orcid":false,"given":"Ruyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"key":"2924_CR1","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation arXiv:1706.05587 [cs.CV]."},{"key":"2924_CR2","doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, S., Zhao, H., & Jia, J. (2021). Distilling knowledge via knowledge review. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 5008\u20135017)","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"2924_CR3","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. Proc. IEEE Conf. Comput. Vis. Pattern Recognit (pp. 3213\u20133223)","DOI":"10.1109\/CVPR.2016.350"},{"key":"2924_CR4","doi-asserted-by":"publisher","first-page":"5363","DOI":"10.1109\/TIP.2021.3083113","volume":"30","author":"Y Feng","year":"2021","unstructured":"Feng, Y., Sun, X., Diao, W., Li, J., & Gao, X. (2021). Double similarity distillation for semantic image segmentation. IEEE Trans. Image Process., 30, 5363\u20135376.","journal-title":"IEEE Trans. Image Process."},{"key":"2924_CR5","doi-asserted-by":"crossref","unstructured":"Gou, J., Xiong, X., Yu, B., and others.(2023). Multi-target knowledge distillation via student self-reflection. International Journal of Computer Vision 131, 1857\u20131874","DOI":"10.1007\/s11263-023-01792-z"},{"key":"2924_CR6","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. Int. J. Comput. Vis., 129, 1789\u20131819.","journal-title":"Int. J. Comput. Vis."},{"key":"2924_CR7","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., & Sun, J. (2017). Channel pruning for accelerating very deep neural networks. Proc. IEEE Int. Conf. Comput. Vis (pp. 1389\u20131397)","DOI":"10.1109\/ICCV.2017.155"},{"key":"2924_CR8","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. Proc. IEEE\/CVF Int. Conf. Comput. Vis (pp. 1921\u20131930)","DOI":"10.1109\/ICCV.2019.00201"},{"key":"2924_CR9","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network arXiv:1503.02531 [cs.LG]."},{"key":"2924_CR10","unstructured":"Hossain, M. I., Akhter, S., Hong, C. S., & Huh, E.-N. (2025). Single teacher, multiple perspectives: Teacher knowledge augmentation for enhanced knowledge distillation. The Thirteenth International Conference on Learning Representations"},{"key":"2924_CR11","doi-asserted-by":"crossref","unstructured":"Huo, F., Xu, W., Guo, J., Wang, H.,& Guo, S.(2024). C2kd: Bridging the modality gap for cross-modal knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 16006\u201316015)","DOI":"10.1109\/CVPR52733.2024.01515"},{"key":"2924_CR12","unstructured":"Jocher, G., Chaurasia, A., & Qiu, J.(2023). Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics. Software"},{"key":"2924_CR13","unstructured":"Kim, S.W., & Kim, H.-E.(2017). Transferring knowledge to smaller network with class-distance loss arXiv:1707.05785 [cs.LG]"},{"key":"2924_CR14","unstructured":"Krizhevsky, A., Hinton, G., and others.(2009). Learning multiple layers of features from tiny images. Technical report, University of Toronto"},{"key":"2924_CR15","doi-asserted-by":"crossref","unstructured":"Li, Q., Jin, S., & Yan, J. (2017). Mimicking very efficient network for object detection. Proc. IEEE Conf. Comput. Vis. Pattern Recognit (pp. 6356\u20136364)","DOI":"10.1109\/CVPR.2017.776"},{"key":"2924_CR16","first-page":"1504","volume":"37","author":"Z Li","year":"2023","unstructured":"Li, Z., Li, X., Yang, L., Zhao, B., Song, R., Luo, L., Li, J., & Yang, J. (2023). Curriculum temperature for knowledge distillation. Proc. AAAI Conf. Artif. Intell., 37, 1504\u20131512.","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2924_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: common objects in context. Proc. Eur. Conf. Comput. Vis (pp. 740\u2013755)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2924_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. Proc. IEEE Conf. Comput. Vis. Pattern Recognit (pp. 2117\u20132125)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2924_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cao, J., Li, B., and others.(2024). Cross-architecture knowledge distillation. International Journal of Computer Vision 132, 2798\u20132824","DOI":"10.1007\/s11263-024-02002-0"},{"key":"2924_CR20","unstructured":"Liu, Y., Shu, C., Wang, J., & Shen, C. (2020). Structured knowledge distillation for dense prediction. Intell: IEEE Trans. Pattern Anal. Mach."},{"key":"2924_CR21","unstructured":"Lukasik, M., Bhojanapalli, S., Menon, A. K., & Kumar, S. (2022). Teacher\u2019s pet: understanding and mitigating biases in distillation. Trans. Mach. Learn. Res,"},{"key":"2924_CR22","unstructured":"Menon, A. K., Rawat, A. S., Reddi, S., Kim, S., & Kumar, S. (2021). A statistical perspective on distillation. Proc. Int. Conf. Mach. Learn (pp. 7632\u20137642)"},{"key":"2924_CR23","first-page":"4233","volume":"38","author":"R Miles","year":"2024","unstructured":"Miles, R., & Mikolajczyk, K. (2024). Understanding the role of the projector in knowledge distillation. Proc. AAAI Conf. Artif. Intell., 38, 4233\u20134241.","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2924_CR24","first-page":"5191","volume":"34","author":"SI Mirzadeh","year":"2020","unstructured":"Mirzadeh, S. I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., & Ghasemzadeh, H. (2020). Improved knowledge distillation via teacher assistant. Proc. AAAI Conf. Artif. Intell., 34, 5191\u20135198.","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2924_CR25","doi-asserted-by":"publisher","first-page":"11037","DOI":"10.52202\/075280-0487","volume":"36","author":"U Ojha","year":"2023","unstructured":"Ojha, U., Li, Y., Sundara Rajan, A., Liang, Y., & Lee, Y. J. (2023). What knowledge gets distilled in knowledge distillation? Adv. Neural Inf. Process. Syst., 36, 11037\u201311048.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2924_CR26","unstructured":"Park, D.Y., Cha, M.-H., Kim, D., Han, B., and others.(2021). Learning student-friendly teacher networks for knowledge distillation. Adv. Neural Inf. Process. Syst., 34, 13292\u201313303"},{"key":"2924_CR27","doi-asserted-by":"crossref","unstructured":"Park, J., & No, A. (2022). Prune your model before distill it. European Conference on Computer Vision (pp. 120\u2013136). Springer.","DOI":"10.1007\/978-3-031-20083-0_8"},{"key":"2924_CR28","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., & Cho, M. (2019). Relational knowledge distillation. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 3967\u20133976)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"2924_CR29","doi-asserted-by":"crossref","unstructured":"Passalis, N., & Tefas, A. (2018). Learning deep representations with probabilistic knowledge transfer. Proc. Eur. Conf. Comput. Vis (pp. 268\u2013284)","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"2924_CR30","doi-asserted-by":"crossref","unstructured":"Patel, G., Mopuri, K. R., & Qiu, Q. (2023). Learning to retain while acquiring: combating distribution-shift in adversarial data-free knowledge distillation. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 7786\u20137794)","DOI":"10.1109\/CVPR52729.2023.00752"},{"issue":"1","key":"2924_CR31","first-page":"82","volume":"10","author":"D Paulin","year":"2012","unstructured":"Paulin, D., & Suneson, K. (2012). Knowledge transfer, knowledge sharing and knowledge barriers: three blurry terms in KM. Electron. J. Knowl. Manag., 10(1), 82\u201392.","journal-title":"Electron. J. Knowl. Manag."},{"key":"2924_CR32","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst, 28,"},{"key":"2924_CR33","unstructured":"Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2014). Fitnets: hints for thin deep nets arXiv:1412.6550 [cs.LG]."},{"key":"2924_CR34","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., and others.(2015). Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252","DOI":"10.1007\/s11263-015-0816-y"},{"key":"2924_CR35","unstructured":"Sadowski, P., Collado, J., Whiteson, D., & Baldi, P. (2015). Deep learning, dark knowledge, and dark matter. NIPS Workshop on High-energy Physics and Machine Learning (pp. 81\u201387)"},{"key":"2924_CR36","unstructured":"Sarridis, I., Koutlis, C., Papadopoulos, S., & Kompatsiaris, I. (2022). Indistill: transferring knowledge from pruned intermediate layers arXiv:2205.10003 [cs.CV]."},{"issue":"1","key":"2924_CR37","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1038\/s41467-023-44383-9","volume":"15","author":"J Shao","year":"2024","unstructured":"Shao, J., Wu, F., & Zhang, J. (2024). Selective knowledge sharing for privacy-preserving federated distillation without a good teacher. Nature Communications, 15(1), 349.","journal-title":"Nature Communications"},{"key":"2924_CR38","doi-asserted-by":"crossref","unstructured":"Shu, C., Liu, Y., Gao, J., Yan, Z., & Shen, C. (2021). Channel-wise knowledge distillation for dense prediction. Proc. IEEE\/CVF Int. Conf. Comput. Vis (pp. 5311\u20135320)","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"2924_CR39","doi-asserted-by":"crossref","unstructured":"Son, W., Na, J., Choi, J., & Hwang, W. (2021). Densely guided knowledge distillation using multiple teacher assistants. Proc. IEEE\/CVF Int. Conf. Comput. Vis (pp. 9395\u20139404)","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"2924_CR40","first-page":"6906","volume":"34","author":"S Stanton","year":"2021","unstructured":"Stanton, S., Izmailov, P., Kirichenko, P., Alemi, A. A., & Wilson, A. G. (2021). Does knowledge distillation really work? Adv. Neural Inf. Process. Syst, 34, 6906\u20136919.","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2924_CR41","doi-asserted-by":"crossref","unstructured":"Su, C.-P., Tseng, C.-H., Pu, B., Zhao, L., Yang, J., Chen, Z., & Lee, S.-J. (2025). Ea-kd: Entropy-based adaptive knowledge distillation. Proc. IEEE\/CVF Int. Conf. Comput. Vis (pp. 731\u2013740)","DOI":"10.1109\/ICCV51701.2025.00076"},{"key":"2924_CR42","doi-asserted-by":"crossref","unstructured":"Sun, S., Ren, W., Li, J., Wang, R., & Cao, X. (2024). Logit standardization in knowledge distillation. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 15731\u201315740)","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"2924_CR43","doi-asserted-by":"crossref","unstructured":"Tang, Z., Wang, D., & Zhang, Z. (2016). Recurrent neural network training with dark knowledge transfer. Proc. IEEE Int. Conf. Acoust. Speech Signal Process (pp. 5900\u20135904)","DOI":"10.1109\/ICASSP.2016.7472809"},{"key":"2924_CR44","unstructured":"Tian, Y., Krishnan, D., & Isola, P. (2019). Contrastive representation distillation arXiv:1910.10699 [cs.CV]."},{"issue":"2","key":"2924_CR45","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1109\/TPAMI.2022.3159581","volume":"45","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Chen, P., Lai, X., Jiang, L., Liu, S., Zhao, H., Yu, B., Yang, M.-C., & Jia, J. (2022). Adaptive perspective distillation for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 45(2), 1372\u20131387.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2924_CR46","doi-asserted-by":"publisher","first-page":"4551","DOI":"10.1109\/TPAMI.2023.3343717","volume":"46","author":"X Tian","year":"2023","unstructured":"Tian, X., Zhang, Z., Wang, C., Zhang, W., Qu, Y., Ma, L., Wu, Z., Xie, Y., & Tao, D. (2023). Variational distillation for multi-view learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46, 4551\u20134566.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"2924_CR47","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","volume":"44","author":"L Wang","year":"2021","unstructured":"Wang, L., & Yoon, K.-J. (2021). Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks. IEEE Trans. Pattern Anal. Mach. Intell., 44(6), 3048\u20133068.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2924_CR48","doi-asserted-by":"crossref","unstructured":"Wang, T., Yuan, L., Zhang, X., & Feng, J. (2019). Distilling object detectors with fine-grained feature imitation. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 4933\u20134942)","DOI":"10.1109\/CVPR.2019.00507"},{"key":"2924_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhou, W., Jiang, T., Bai, X., & Xu, Y. (2020). Intra-class feature variation distillation for semantic segmentation. Proc. Eur. Conf. Comput. Vis (pp. 346\u2013362)","DOI":"10.1007\/978-3-030-58571-6_21"},{"key":"2924_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, H., Chau, L.-P., & Kot, A. C. (2021). Embracing the dark knowledge: Domain generalization using regularized knowledge distillation. Proceedings of the 29th ACM International Conference on Multimedia (pp. 2595\u20132604)","DOI":"10.1145\/3474085.3475434"},{"key":"2924_CR51","doi-asserted-by":"crossref","unstructured":"Xiang, L., Gao, J., & Xu, C. (2025). Evidential knowledge distillation. Proc. IEEE\/CVF Int. Conf. Comput. Vis (pp. 2814\u20132824)","DOI":"10.1109\/ICCV51701.2025.00270"},{"key":"2924_CR52","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural Inf. Process. Syst, 34, 12077\u201312090.","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2924_CR53","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhu, X., Bulat, A., and others.(2025). Knowledge distillation meets open-set semi-supervised learning. International Journal of Computer Vision 133, 315\u2013334","DOI":"10.1007\/s11263-024-02192-7"},{"key":"2924_CR54","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., & Zhang, Q. (2022). Cross-image relational knowledge distillation for semantic segmentation. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 12319\u201312328)","DOI":"10.1109\/CVPR52688.2022.01200"},{"issue":"6","key":"2924_CR55","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 Trans. Pattern Anal. Mach. Intell., 46(6), 4188\u20134205.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2924_CR56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129745","volume":"636","author":"S Yang","year":"2025","unstructured":"Yang, S., Yang, X., Ren, J., Xu, L., Yang, J., Huang, Z., Gong, Z., & Wang, W. (2025). Adaptive temperature distillation method for mining hard samples\u2019 knowledge. Neurocomputing, 636, Article 129745.","journal-title":"Neurocomputing"},{"key":"2924_CR57","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., & Kim, J. (2017). A gift from knowledge distillation: fast optimization, network minimization and transfer learning. Proc. IEEE Conf. Comput. Vis. Pattern Recognit (pp. 4133\u20134141)","DOI":"10.1109\/CVPR.2017.754"},{"key":"2924_CR58","unstructured":"Zagoruyko, S., & Komodakis, N. (2016). Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer arXiv:1612.03928 [cs.CV]."},{"key":"2924_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, J., Gao, Y., Zhou, M., Liu, R., Cheng, X., Nikoli\u0107, S. V., & Chen, S. (2025). Svd-kd: SVD-based hidden layer feature extraction for knowledge distillation. Pattern Recognit, 111721.","DOI":"10.1016\/j.patcog.2025.111721"},{"key":"2924_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lan, Z., Dai, Y., Zeng, F., Bai, Y., Chang, J., & Wei, Y. (2020). Prime-aware adaptive distillation. Proc. Eur. Conf. Comput. Vis (pp. 658\u2013674)","DOI":"10.1007\/978-3-030-58529-7_39"},{"key":"2924_CR61","first-page":"22434","volume":"39","author":"J Zhang","year":"2025","unstructured":"Zhang, J., Gao, Y., Liu, R., Cheng, X., Zhang, H., & Chen, S. (2025). Can students beyond the teacher? distilling knowledge from teacher\u2019s bias. Proc. AAAI Conf. Artif. Intell., 39, 22434\u201322442.","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2924_CR62","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., & Liang, J. (2022). Decoupled knowledge distillation. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 11953\u201311962)","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"2924_CR63","doi-asserted-by":"crossref","unstructured":"Zhou, W., Xu, C.,& McAuley, J.(2022). BERT learns to teach: knowledge distillation with meta learning. In: Proc. Annu. Meet. Assoc. Comput. Linguist.,(pp. 7037\u20137049)","DOI":"10.18653\/v1\/2022.acl-long.485"},{"key":"2924_CR64","unstructured":"Zhou, Z., Zhuge, C., Guan, X., & Liu, W. (2020). Channel distillation: channel-wise attention for knowledge distillation arXiv:2006.01683 [cs.CV]."},{"key":"2924_CR65","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024). Vision mamba: efficient visual representation learning with bidirectional state space model. Proc. Int. Conf. Mach. Learn.,235, 62429\u201362442."},{"key":"2924_CR66","doi-asserted-by":"crossref","unstructured":"Zhu, Y., & Wang, Y. (2021). Student customized knowledge distillation: bridging the gap between student and teacher. Proc. IEEE\/CVF Int. Conf. Comput. Vis (pp. 5057\u20135066)","DOI":"10.1109\/ICCV48922.2021.00501"},{"key":"2924_CR67","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. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit (pp. 9260\u20139269)","DOI":"10.1109\/CVPR46437.2021.00914"},{"key":"2924_CR68","doi-asserted-by":"publisher","first-page":"32011","DOI":"10.52202\/068431-2320","volume":"35","author":"Y Zhu","year":"2022","unstructured":"Zhu, Y., Liu, N., Xu, Z., Liu, X., Meng, W., Wang, L., Ou, Z., & Tang, J. (2022). Teach less, learn more: on the undistillable classes in knowledge distillation. Adv. Neural Inf. Process. Syst., 35, 32011\u201332024.","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02924-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02924-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02924-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T05:50:31Z","timestamp":1785304231000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02924-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":68,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2924"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02924-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"10 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":3,"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"}}],"article-number":"337"}}