{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:18:35Z","timestamp":1787159915566,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031376597","type":"print"},{"value":"9783031376603","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-37660-3_20","type":"book-chapter","created":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T02:02:20Z","timestamp":1690596140000},"page":"289-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing the\u00a0Linear Probing Performance of\u00a0Masked Auto-Encoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0010-7508","authenticated-orcid":false,"given":"Yurui","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,30]]},"reference":[{"key":"20_CR1","unstructured":"Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image transformers. In: ICLR (2022)"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"20_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chen*, X., Xie*, S., He, K.: An empirical study of training self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"20_CR6","unstructured":"Clark, K., Luong, M.T., Le, Q.V., Manning, C.D.: Electra: pre-training text encoders as discriminators rather than generators. In: ICLR (2020)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: Randaugment: practical automated data augmentation with a reduced search space. In: NeuIPS (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (Jun 2019)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"20_CR11","unstructured":"Dong, X., et al.: PECO: perceptual codebook for BERT pre-training of vision transformers. arXiv:2111.12710 (2021)"},{"key":"20_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"20_CR13","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)"},{"key":"20_CR14","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"20_CR17","unstructured":"Hinton, G.E., Zemel, R.: Autoencoders, minimum description length and helmholtz free energy. In: NeuIPS (1993)"},{"key":"20_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"20_CR19","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv:1607.06450 (2016)"},{"key":"20_CR20","unstructured":"von K\u00fcgelgen, J., et al.: Self-supervised learning with data augmentations provably isolates content from style. In: NeuIPS (2021)"},{"key":"20_CR21","unstructured":"Li, Z., et al.: MST: masked self-supervised transformer for visual representation. In: NeurIPS (2021)"},{"key":"20_CR22","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. In: arXiv:1907.11692 (2019)"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR24","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with restarts. In: ICLR (2016)"},{"key":"20_CR25","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in ADAM. In: ICLR (2017)"},{"key":"20_CR26","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv:1807.03748 (2018)"},{"key":"20_CR27","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"20_CR29","unstructured":"Tan, H., Lei, J., Wolf, T., Bansal, M.: VIMPAC: video pre-training via masked token prediction and contrastive learning. arXiv:2106.11250 (2021)"},{"key":"20_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"20_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeuIPS (2017)"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C., Yuille, A.L., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. arXiv:2112.09133 (2021)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SIMMIM: a simple framework for masked image modeling. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"20_CR34","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Scaling SGD batch size to 32k for imagenet training. arXiv:1708.03888 (2017)"},{"key":"20_CR35","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"20_CR36","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: ICML (2021)"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2017)","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"20_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Split-brain autoencoders: unsupervised learning by cross-channel prediction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.76"},{"key":"20_CR40","unstructured":"Zhou, J., et al.: ibot: image Bert pre-training with online tokenizer. In: ICLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-37660-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T02:06:45Z","timestamp":1690596405000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-37660-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031376597","9783031376603"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-37660-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montr\u00e9al, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icpr2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}