{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:48:26Z","timestamp":1777654106515,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680595","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"4543-4552","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Student-Oriented Teacher Knowledge Refinement for Knowledge Distillation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9389-6472","authenticated-orcid":false,"given":"Chaomin","family":"Shen","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8195-4978","authenticated-orcid":false,"given":"Yaomin","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3558-0402","authenticated-orcid":false,"given":"HaoKun","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0851-8924","authenticated-orcid":false,"given":"Jinsong","family":"Fan","sequence":"additional","affiliation":[{"name":"Wenzhou University, Wenzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2568-4691","authenticated-orcid":false,"given":"Guixu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2011, Fort Lauderdale, USA, April 11-13, 2011 (JMLR Proceedings","volume":"172","author":"Bengio Yoshua","year":"2011","unstructured":"Yoshua Bengio, Fr\u00e9d\u00e9ric Bastien, Arnaud Bergeron, Nicolas Boulanger-Lewandowski, Thomas M. Breuel, Youssouf Chherawala, Moustapha Ciss\u00e9, Myriam C\u00f4t\u00e9, Dumitru Erhan, Jeremy Eustache, Xavier Glorot, Xavier Muller, Sylvain Pannetier Lebeuf, Razvan Pascanu, Salah Rifai, Fran\u00e7ois Savard, and Guillaume Sicard. 2011. Deep Learners Benefit More from Out-of-Distribution Examples. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2011, Fort Lauderdale, USA, April 11-13, 2011 (JMLR Proceedings, Vol. 15), Geoffrey J. Gordon, David B. Dunson, and Miroslav Dud\u00edk (Eds.). JMLR.org, 164--172. http:\/\/proceedings.mlr.press\/v15\/bengio11b\/ bengio11b.pdf"},{"key":"e_1_3_2_1_2_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. PMLR, 552--560","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Gr\u00e9goire Mesnil, Yann Dauphin, and Salah Rifai. 2013. Better mixing via deep representations. In International Conference on Machine Learning. PMLR, 552--560."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16-21 June 2013 (JMLR Workshop and Conference Proceedings","volume":"560","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Gr\u00e9goire Mesnil, Yann N. Dauphin, and Salah Rifai. 2013. Better Mixing via Deep Representations. In Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16-21 June 2013 (JMLR Workshop and Conference Proceedings, Vol. 28). JMLR.org, 552--560. http:\/\/proceedings.mlr.press\/v28\/bengio13.html"},{"key":"e_1_3_2_1_5_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Chen Guobin","year":"2017","unstructured":"Guobin Chen, Wongun Choi, Xiang Yu, Tony Han, and Manmohan Chandraker. 2017. Learning efficient object detection models with knowledge distillation. In Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910052"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","volume-title":"Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries and Graham W Taylor. 2017. Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538 (2017)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01145"},{"key":"e_1_3_2_1_11_1","volume-title":"Deep manifold traversal: Changing labels with convolutional features. arXiv preprint arXiv:1511.06421","author":"Gardner Jacob R","year":"2015","unstructured":"Jacob R Gardner, Paul Upchurch, Matt J Kusner, Yixuan Li, Kilian Q Weinberger, Kavita Bala, and John E Hopcroft. 2015. Deep manifold traversal: Changing labels with convolutional features. arXiv preprint arXiv:1511.06421 (2015)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01792-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"e_1_3_2_1_15_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_16_1","volume-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02325"},{"key":"e_1_3_2_1_18_1","volume-title":"Co-Mixup: Saliency guided joint mixup with supermodular diversity. arXiv preprint arXiv:2102.03065","author":"Kim Jang-Hyun","year":"2021","unstructured":"Jang-Hyun Kim, Wonho Choo, Hosan Jeong, and Hyun Oh Song. 2021. Co-Mixup: Saliency guided joint mixup with supermodular diversity. arXiv preprint arXiv:2102.03065 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"e_1_3_2_1_20_1","volume-title":"Learning multiple layers of features from tiny images. Master?s thesis. Department of Computer Science","author":"Krizhevsky Alex","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Master?s thesis. Department of Computer Science, University of Toronto."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00876"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612281"},{"key":"e_1_3_2_1_24_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Lim Sungbin","year":"2019","unstructured":"Sungbin Lim, Ildoo Kim, Taesup Kim, Chiheon Kim, and Sungwoong Kim. 2019. Fast autoaugment. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00756"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_32_1","volume-title":"Deep Directed Generative Autoencoders. CoRR abs\/1410.0630","author":"Ozair Sherjil","year":"2014","unstructured":"Sherjil Ozair and Yoshua Bengio. 2014. Deep Directed Generative Autoencoders. CoRR abs\/1410.0630 (2014). arXiv:1410.0630 http:\/\/arxiv.org\/abs\/1410.0630"},{"key":"e_1_3_2_1_33_1","volume-title":"Deep directed generative autoencoders. arXiv preprint arXiv:1410.0630","author":"Ozair Sherjil","year":"2014","unstructured":"Sherjil Ozair and Yoshua Bengio. 2014. Deep directed generative autoencoders. arXiv preprint arXiv:1410.0630 (2014)."},{"key":"e_1_3_2_1_34_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"1912","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv:1912.01703 [cs.LG]"},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems, Vol. 28."},{"key":"e_1_3_2_1_36_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2014","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. FitNets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"e_1_3_2_1_40_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and AndrewZisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning. PMLR, 4723--4731","author":"Srinivas Suraj","year":"2018","unstructured":"Suraj Srinivas and Fran\u00e7ois Fleuret. 2018. Knowledge transfer with Jacobian matching. In International Conference on Machine Learning. PMLR, 4723--4731."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"e_1_3_2_1_43_1","volume-title":"Contrastive representation distillation. arXiv preprint arXiv:1910.10699","author":"Tian Yonglong","year":"2019","unstructured":"Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2019. Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.645"},{"key":"e_1_3_2_1_46_1","volume-title":"International Conference on Machine Learning. PMLR, 6438--6447","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold mixup: Better representations by interpolating hidden states. In International Conference on Machine Learning. PMLR, 6438--6447."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/384"},{"key":"e_1_3_2_1_48_1","unstructured":"Yuxin Wu Alexander Kirillov Francisco Massa Wan-Yen Lo and Ross Girshick. 2019. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"e_1_3_2_1_51_1","volume-title":"From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels. arXiv preprint arXiv:2303.13005","author":"Yang Zhendong","year":"2023","unstructured":"Zhendong Yang, Ailing Zeng, Zhe Li, Tianke Zhang, Chun Yuan, and Yu Li. 2023. From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels. arXiv preprint arXiv:2303.13005 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00065"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_1_55_1","volume-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)."},{"key":"e_1_3_2_1_56_1","volume-title":"Wide residual networks. arXiv preprint arXiv:1605.07146","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)."},{"key":"e_1_3_2_1_57_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"e_1_3_2_1_61_1","volume-title":"Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578","author":"Zoph Barret","year":"2016","unstructured":"Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680595","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":61,"alternative-id":["10.1145\/3664647.3680595","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680595","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}