{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:51:57Z","timestamp":1767340317246,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031728549"},{"type":"electronic","value":"9783031728556"}],"license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72855-6_22","type":"book-chapter","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T18:49:25Z","timestamp":1731091765000},"page":"379-396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["The Role of\u00a0Masking for\u00a0Efficient Supervised Knowledge Distillation of\u00a0Vision Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1082-5949","authenticated-orcid":false,"given":"Seungwoo","family":"Son","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2275-6880","authenticated-orcid":false,"given":"Jegwang","family":"Ryu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5208-2007","authenticated-orcid":false,"given":"Namhoon","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1349-8595","authenticated-orcid":false,"given":"Jaeho","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Masked Siamese networks for label-efficient learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: ICCV, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Beyer, L., Zhai, X., Royer, A., Markeeva, L., Anil, R., Kolesnikov, A.: Knowledge distillation: a good teacher is patient and consistent. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"22_CR4","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: ICLR (2023)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"22_CR6","unstructured":"Chefer, H., Schwartz, I., Wolf, L.: Optimizing relevance maps of vision transformers improves robustness. In: NeurIPS (2022)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: SdAE: self-distillated masked autoencoder. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20056-4_7"},{"key":"22_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: audio spectrogram transformer. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"key":"22_CR10","unstructured":"Goyal, S., Choudhury, A.R., Raje, S.M., Chakaravarthy, V.T., Sabharwal, Y., Verma, A.: PoWER-BERT: accelerating BERT inference via progressive word-vector elimination. In: ICML (2020)"},{"key":"22_CR11","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"22_CR12","unstructured":"Hao, Z., et al.: Learning efficient vision transformers via fine-grained manifold distillation. In: NeurIPS (2022)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"22_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Huang, W., Peng, Z., Dong, L., Wei, F., Jiao, J., Ye, Q.: Generic-to-specific distillation of masked autoencoders. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01535"},{"key":"22_CR16","unstructured":"Huang, Y., et al.: GPipe: efficient training of giant neural networks using pipeline parallelism. In: NeurIPS (2019)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Jin, X., et al.: Knowledge distillation via route constrained optimization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00143"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Kim, M., Gao, S., Hsu, Y.C., Shen, Y., Jin, H.: Token fusion: bridging the gap between token pruning and token merging. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1383\u20131392 (2024)","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via soft token pruning. In: European Conference on Computer Vision (2021)","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"22_CR21","unstructured":"Li, J., et al.: Progressively compressed auto-encoder for self-supervised representation learning. In: ICLR (2022)"},{"key":"22_CR22","unstructured":"Li, Y., Xu, S., Zhang, B., Cao, X., Gao, P., Guo, G.: Q-ViT: accurate and fully quantized low-bit vision transformer. In: NeurIPS (2022)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Curriculum temperature for knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1504\u20131512 (2023)","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"22_CR24","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. In: ICLR (2022)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Marin, D., Chang, J.H.R., Ranjan, A., Prabhu, A., Rastegari, M., Tuzel, O.: Token pooling in vision transformers for image classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2023)","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Meng, L., Li, H., Chen, B.C., Lan, S., Wu, Z., Jiang, Y.G., Lim, S.N.: AdaViT: adaptive vision transformers for efficient image recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S.I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"22_CR29","unstructured":"Peng, Z., Dong, L., Bao, H., Wei, F., Ye, Q.: A unified view of masked image modeling. Trans. Mach. Learn. Res. (2023)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Piczak, K.J.: ESC: dataset for environmental sound classification. In: Proceedings of the ACM International Conference on Multimedia (2015)","DOI":"10.1145\/2733373.2806390"},{"key":"22_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"22_CR32","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: NeurIPS (2021)"},{"key":"22_CR33","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Shen, Z., Xing, E.P.: A fast knowledge distillation framework for visual recognition. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_39"},{"key":"22_CR35","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., Pouransari, H., Faghri, F., Vemulapalli, R., Tuzel, O.: MobileCLIP: fast image-text models through multi-modal reinforced training. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"22_CR38","unstructured":"Wang, K., Yang, F., van\u00a0de Weijer, J.: Attention distillation: self-supervised vision transformer students need more guidance. In: British Machine Vision Conference (2022)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"22_CR40","unstructured":"Wu, H., et al.: Self-supervised models are good teaching assistants for vision transformers. In: ICML (2022)"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J.M., Mallya, A., Kautz, J., Molchanov, P.: A-ViT: adaptive tokens for efficient vision transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"22_CR43","unstructured":"Yu, S., et al.: Unified visual transformer compression. In: ICLR (2022)"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Yun, S., Oh, S.J., Heo, B., Han, D., Choe, J., Chun, S.: Re-labeling ImageNet: from single to multi-labels, from global to localized labels. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00237"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"22_CR46","unstructured":"Zhang, C., et al.: Faster segment anything: towards lightweight SAM for mobile applications. arXiv preprint arXiv:2306.14289 (2023)"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: MiniViT: compressing vision transformers with weight multiplexing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12145\u201312154 (2022)","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"22_CR48","unstructured":"Zhang, S., Zhu, F., Zhao, R., Yan, J.: Contextual image masking modeling via synergized contrasting without view augmentation for faster and better visual pretraining. In: ICLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72855-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T19:07:06Z","timestamp":1731092826000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72855-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"ISBN":["9783031728549","9783031728556"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72855-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,9]]},"assertion":[{"value":"9 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}