{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T03:10:48Z","timestamp":1783825848973,"version":"3.55.0"},"reference-count":105,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11263-023-01852-4","type":"journal-article","created":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T09:04:32Z","timestamp":1693213472000},"page":"208-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":235,"title":["Context Autoencoder for Self-supervised Representation Learning"],"prefix":"10.1007","volume":"132","author":[{"given":"Xiaokang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Xin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shentong","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shumin","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,28]]},"reference":[{"key":"1852_CR1","unstructured":"Asano, Y.\u00a0M., Rupprecht, C., & Vedaldi, A. (2019). Self-labelling via simultaneous clustering and representation learning. arXiv:1911.05371"},{"key":"1852_CR2","unstructured":"Atito, S., Awais, M., & Kittler, J. (2021). Sit: Self-supervised vision transformer. arXiv:2104.03602"},{"key":"1852_CR3","volume-title":"data2vec: A general framework for self-supervised learning in Speech","author":"A Baevski","year":"2022","unstructured":"Baevski, A., Hsu, W.-N., Xu, Q., Babu, A., Gu, J., & Auli, M. (2022). data2vec: A general framework for self-supervised learning in Speech. Technical report: Vision and Languags."},{"key":"1852_CR4","unstructured":"Bao, H., Dong, L., & Wei, F. (2021). BEiT: BERT pre-training of image transformers. arXiv:2106.08254"},{"key":"1852_CR5","unstructured":"Bardes, A., Ponce, J., & LeCun, Y. (2021). Vicreg: Variance-invariance-covariance regularization for self-supervised learning. arXiv:2105.04906"},{"key":"1852_CR6","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Van\u00a0Gool, L. (2014). Food-101\u2014Mining discriminative components with random forests. In ECCV.","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"1852_CR7","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2021","unstructured":"Cai, Z., & Vasconcelos, N. (2021). Cascade r-cnn: High quality object detection and instance segmentation. TPAMI, 43, 1483\u20131498.","journal-title":"TPAMI"},{"key":"1852_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018). Deep clustering for unsupervised learning of visual features. In ECCV (pp. 132\u2013149).","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"1852_CR9","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Mairal, J., & Joulin, A. (2019). Unsupervised pre-training of image features on non-curated data. In ICCV (pp. 2959\u20132968).","DOI":"10.1109\/ICCV.2019.00305"},{"key":"1852_CR10","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. arXiv:2006.09882."},{"key":"1852_CR11","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A. (2021). Emerging properties in self-supervised vision transformers. CoRR, arxiv:2104.14294.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"1852_CR12","doi-asserted-by":"crossref","unstructured":"Castrejon, L., Aytar, Y., Vondrick, C., Pirsiavash, H., & Torralba, A. (2016). Learning aligned cross-modal representations from weakly aligned data. In CVPR (pp. 2940\u20132949).","DOI":"10.1109\/CVPR.2016.321"},{"key":"1852_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., & He, K. (2021). Exploring simple Siamese representation learning. In CVPR (pp. 15750\u201315758).","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"1852_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Q., Chen, X., Wang, J., Feng, H., Han, J., Ding, E., Zeng, G., & Wamg, J. (2022). Group detr: Fast detr training with group-wise one-to-many assignment.","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"1852_CR15","doi-asserted-by":"crossref","unstructured":"Chen, X., Ding, M., Wang, X., Xin, Y., Mo, S., Wang, Y., Han, S., Luo, P., Zeng, G., & Wang, J. (2022). Context autoencoder for self-supervised representation learning. CoRR, arxiv:2202.03026.","DOI":"10.1007\/s11263-023-01852-4"},{"key":"1852_CR16","unstructured":"Chen, J., Hu, M., Li, B., & Elhoseiny, M. (2022). Efficient self-supervised vision pretraining with local masked reconstruction. arXiv:2206.00790"},{"key":"1852_CR17","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G.\u00a0E. (2020). A simple framework for contrastive learning of visual representations. In ICML, volume 119 of Proceedings of Machine Learning Research (pp. 1597\u20131607). PMLR."},{"key":"1852_CR18","unstructured":"Chen, M., Radford, A., Child, R., Wu, J., Jun, H., Luan, D., & Sutskever, I. (2020). Generative pretraining from pixels. In ICML (pp. 1691\u20131703). PMLR."},{"key":"1852_CR19","unstructured":"Chen, Q., Wang, J., Han, C., Zhang, S., Li, Z., Chen, X., Chen, J., Wang, X., Han, S., Zhang, G., Feng, H., Yao, K., Han, J., Ding, E., & Wang, J. (2022). Group DETR v2: Strong object detector with encoder-decoder pretraining. CoRR, arxiv:2211.03594."},{"key":"1852_CR20","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C.\u00a0C., & Lin, D. (2019). MMDetection: Open mmlab detection toolbox and benchmark. arXiv:1906.07155."},{"key":"1852_CR21","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., & Kaiming, H. (2021). An empirical study of training self-supervised vision transformers. CoRR, arxiv:2104.02057.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"1852_CR22","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 CVPR (pp. 248\u2013255). IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1852_CR23","first-page":"4171","volume-title":"NAACL-HLT","author":"J Devlin","year":"2019","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In J. Burstein, C. Doran, & T. Solorio (Eds.), NAACL-HLT (pp. 4171\u20134186). Association for Computational Linguistics."},{"key":"1852_CR24","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., & Efros, Alexei, A. (2015). Unsupervised visual representation learning by context prediction. In ICCV.","DOI":"10.1109\/ICCV.2015.167"},{"key":"1852_CR25","unstructured":"Dong, X., Bao, J., Zhang, T., Chen, D., Zhang, Weiming,Y., Lu, C., Dong, W., Fang, & Yu, N. (2021). Peco: Perceptual codebook for bert pre-training of vision transformers. arXiv:2111.12710."},{"key":"1852_CR26","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR: OpenReview.net."},{"issue":"9","key":"1852_CR27","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1109\/TPAMI.2015.2496141","volume":"38","author":"A Dosovitskiy","year":"2015","unstructured":"Dosovitskiy, A., Fischer, P., Springenberg, J. T., Riedmiller, M., & Brox, T. (2015). Discriminative unsupervised feature learning with exemplar convolutional neural networks. TPAMI, 38(9), 1734\u20131747.","journal-title":"TPAMI"},{"key":"1852_CR28","first-page":"766","volume":"27","author":"A Dosovitskiy","year":"2014","unstructured":"Dosovitskiy, A., Springenberg, J. T., Riedmiller, M., & Brox, T. (2014). Discriminative unsupervised feature learning with convolutional neural networks. NeurIPS, 27, 766\u2013774.","journal-title":"NeurIPS"},{"key":"1852_CR29","unstructured":"El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., & Grave, E. (2021). Are large-scale datasets necessary for self-supervised pre-training? arXiv:2112.10740"},{"key":"1852_CR30","unstructured":"Ermolov, A., Siarohin, A., Sangineto, E., & Sebe, N. (2021). Whitening for self-supervised representation learning. In ICML (pp. 3015\u20133024). PMLR."},{"key":"1852_CR31","unstructured":"Fang, Y., Dong, L., Bao, H., Wang, X., & Wei, F. (2022). Corrupted image modeling for self-supervised visual pre-training. arXiv:2202.03382"},{"key":"1852_CR32","unstructured":"Gallinari, P., Lecun, Y., Thiria, S., & Soulie, F.\u00a0F. (1987). M\u00e9moires associatives distribu\u00e9es: une comparaison (distributed associative memories: A comparison). In Proceedings of COGNITIVA 87, Paris, La Villette, May 1987. Cesta-Afcet."},{"key":"1852_CR33","unstructured":"Garrido, Q., Chen, Y., Bardes, A., Najman, L. (2022). On the duality between contrastive and non-contrastive self-supervised learning. CoRR, arXiv:2206.02574"},{"key":"1852_CR34","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Bursuc, A., Komodakis, N., P\u00e9rez, P., & Cord, M. (2020). Learning representations by predicting bags of visual words. In CVPR (pp. 6928\u20136938).","DOI":"10.1109\/CVPR42600.2020.00696"},{"key":"1852_CR35","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Bursuc, A., Puy, G., Komodakis, N., Cord, M., & P\u00e9rez, P. (2020). Online bag-of-visual-words generation for unsupervised representation learning. arXiv:2012.11552","DOI":"10.1109\/CVPR46437.2021.00676"},{"key":"1852_CR36","unstructured":"Goyal, P., Caron, M., Lefaudeux, B., Xu, M., Wang, P., Pai, V., Singh, M., Liptchinsky, V., Misra, I., Joulin, A., et\u00a0al. (2021). Self-supervised pretraining of visual features in the wild. arXiv:2103.01988"},{"key":"1852_CR37","unstructured":"Grill, J.-B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P.\u00a0H., Buchatskaya, E., Doersch, C., Pires, B.\u00a0A., Guo, Z.\u00a0D., Azar, M.\u00a0G., et\u00a0al. (2020). Bootstrap your own latent: A new approach to self-supervised learning. arXiv:2006.07733"},{"key":"1852_CR38","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1852_CR39","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R.\u00a0B. (2020). Momentum contrast for unsupervised visual representation learning. In CVPR (pp. 9726\u20139735). Computer Vision Foundation\/IEEE.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1852_CR40","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In ICCV (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"1852_CR41","unstructured":"Henaff, O. (2020). Data-efficient image recognition with contrastive predictive coding. In ICML (pp. 4182\u20134192). PMLR."},{"issue":"5786","key":"1852_CR42","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504\u2013507.","journal-title":"Science"},{"key":"1852_CR43","first-page":"3","volume":"6","author":"GE Hinton","year":"1994","unstructured":"Hinton, G. E., & Zemel, R. S. (1994). Autoencoders, minimum description length, and helmholtz free energy. NeurIPS, 6, 3\u201310.","journal-title":"NeurIPS"},{"key":"1852_CR44","unstructured":"Huang, J., Dong, Q., Gong, S., & Zhu, X. (2019). Unsupervised deep learning by neighbourhood discovery. In ICML (pp. 2849\u20132858). PMLR."},{"key":"1852_CR45","doi-asserted-by":"crossref","unstructured":"Huang, Z., Jin, X., Lu, C., Hou, Q., Cheng, M.-M., Fu, D., Shen, X., & Feng, J. (2022). Contrastive masked autoencoders are stronger vision learners. arXiv:2207.13532","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"1852_CR46","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K.\u00a0Q. (2016). Deep networks with stochastic depth. In ECCV (pp. 646\u2013661). Springer.","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"1852_CR47","unstructured":"Huang, L., You, S., Zheng, M., Wang, F., Qian, C., & Yamasaki, T. (2022). Green hierarchical vision transformer for masked image modeling. arXiv:2205.13515"},{"key":"1852_CR48","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML."},{"key":"1852_CR49","unstructured":"Jing, L., Zhu, J., & LeCun, Y. (2022). Masked siamese convnets. arXiv:2206.07700"},{"key":"1852_CR50","doi-asserted-by":"crossref","unstructured":"Kakogeorgiou, I., Gidaris, S., Psomas, B., Avrithis, Y., Bursuc, A., Karantzalos, K., & Komodakis, N. (2022). What to hide from your students: Attention-guided masked image modeling. In ECCV.","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"1852_CR51","unstructured":"Kingma, Diederik\u00a0P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv:1312.6114."},{"key":"1852_CR52","doi-asserted-by":"crossref","unstructured":"Kong, X., & Zhang, X. (2022). Understanding masked image modeling via learning occlusion invariant feature. arXiv:2208.04164","DOI":"10.1109\/CVPR52729.2023.00604"},{"key":"1852_CR53","unstructured":"LeCun, Y. (1987). Mod\u2018eles connexionistes de l\u2019apprentissage. PhD thesis, Universit\u2019e de Paris VI."},{"key":"1852_CR54","doi-asserted-by":"crossref","unstructured":"Li, X., Ge, Y., Yi, K., Hu, Z., Shan, Y., & Duan, L.-Y. (2022). mc-beit: Multi-choice discretization for image bert pre-training. In ECCV.","DOI":"10.1007\/978-3-031-20056-4_14"},{"key":"1852_CR55","unstructured":"Li, X., Wang, W., Yang, L., & Yang, J. (2022). Uniform masking: Enabling mae pre-training for pyramid-based vision transformers with locality. arXiv:2205.10063"},{"key":"1852_CR56","unstructured":"Li, S., Wu, D., Wu, F., Zang, Z., Wang, K., Shang, L., Sun, B., Li, H., Li, S., et\u00a0al. (2022). Architecture-agnostic masked image modeling-from vit back to cnn. arXiv:2205.13943"},{"key":"1852_CR57","unstructured":"Li, G., Zheng, H., Liu, D., Su, B., & Zheng, C. (2022). Semmae: Semantic-guided masking for learning masked autoencoders. arXiv:2206.10207"},{"key":"1852_CR58","unstructured":"Li, J., Zhou, P., Xiong, C., & Hoi, S. C. H. (2020). Prototypical contrastive learning of unsupervised representations. arXiv:2005.04966"},{"key":"1852_CR59","first-page":"13165","volume":"34","author":"Z Li","year":"2021","unstructured":"Li, Z., Chen, Z., Yang, F., Li, W., Zhu, Y., Zhao, C., Deng, R., Liwei, W., Zhao, R., Tang, M., et al. (2021). Mst: Masked self-supervised transformer for visual representation. NeurIPS, 34, 13165\u201313176.","journal-title":"NeurIPS"},{"key":"1852_CR60","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Lawrence Zitnick, C. (2014). Microsoft coco: Common objects in context. In ECCV (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1852_CR61","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., Wei, F. & Guo, B. (2021). Swin transformer v2: Scaling up capacity and resolution. Cornell University.","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"1852_CR62","doi-asserted-by":"crossref","unstructured":"Liu, H., Jiang, X., Li, X., Guo, A., Jiang, D., & Ren, B. (2022). The devil is in the frequency: Geminated gestalt autoencoder for self-supervised visual pre-training. arXiv:2204.08227","DOI":"10.1609\/aaai.v37i2.25252"},{"key":"1852_CR63","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv:1711.05101"},{"key":"1852_CR64","doi-asserted-by":"crossref","unstructured":"Noroozi, M., & Favaro, P. (2016). Unsupervised learning of visual representations by solving jigsaw puzzles. In ECCV (pp. 69\u201384). Springer.","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"1852_CR65","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016). Context encoders: Feature learning by inpainting. In CVPR (pp. 2536\u20132544).","DOI":"10.1109\/CVPR.2016.278"},{"key":"1852_CR66","doi-asserted-by":"crossref","unstructured":"Peng, X., Wang, K., Zhu, Z., & You, Y. (2022). Crafting better contrastive views for siamese representation learning. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01556"},{"key":"1852_CR67","volume-title":"Understanding self-supervised pretraining with part-aware representation learning","author":"J Qi","year":"2023","unstructured":"Qi, J., Zhu, J., Ding, M., Chen, X., Luo, P., Wang, L., Wang, X., Liu, W., & Wang, J. (2023). Understanding self-supervised pretraining with part-aware representation learning. Report: Tech."},{"key":"1852_CR68","first-page":"8821","volume-title":"ICML","author":"A Ramesh","year":"2021","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021). Zero-shot text-to-image generation. In M. Meila & T. Zhang (Eds.), ICML (Vol. 139, pp. 8821\u20138831). PMLR."},{"key":"1852_CR69","first-page":"1137","volume":"19","author":"M Ranzato","year":"2007","unstructured":"Ranzato, M., Poultney, C., Chopra, S., LeCun, Y., et al. (2007). Efficient learning of sparse representations with an energy-based model. NeurIPS, 19, 1137.","journal-title":"NeurIPS"},{"issue":"3","key":"1852_CR70","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Hao, S., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. IJCV, 115(3), 211\u2013252.","journal-title":"IJCV"},{"key":"1852_CR71","doi-asserted-by":"crossref","unstructured":"Tao, C., Zhu, X., Huang, G., Qiao, Y., Wang, X. & Dai, J. (2022). Siamese image modeling for self-supervised vision representation learning. arXiv:2206.01204","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"1852_CR72","doi-asserted-by":"crossref","unstructured":"Tian, Y., Xie, L., Fang, J., Shi, M., Peng, J., Zhang, X., Jiao, J., Tian, Q., & Ye, Q. (2022). Beyond masking: Demystifying token-based pre-training for vision transformers. arXiv:2203.14313","DOI":"10.2139\/ssrn.4354042"},{"key":"1852_CR73","unstructured":"Tian, Y., Xie, L., Zhang, X., Fang, J., Xu, H., Huang, W., Jiao, J., Tian, Q., & Ye, Q. (2021). Semantic-aware generation for self-supervised visual representation learning. arXiv:2111.13163"},{"key":"1852_CR74","first-page":"6827","volume":"33","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., & Isola, P. (2020). What makes for good views for contrastive learning? NeurIPS, 33, 6827\u20136839.","journal-title":"NeurIPS"},{"key":"1852_CR75","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., & J\u00e9gou, H. (2020). Training data-efficient image transformers & distillation through attention. arXiv:2012.12877"},{"key":"1852_CR76","unstructured":"van den Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv:1807.03748"},{"key":"1852_CR77","unstructured":"Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-sne. Journal of Machine Learning Research,9(11)."},{"key":"1852_CR78","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008). Extracting and composing robust features with denoising autoencoders. In ICML (pp. 1096\u20131103).","DOI":"10.1145\/1390156.1390294"},{"key":"1852_CR79","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P.-A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 11, 3371\u20133408.","journal-title":"Journal of Machine Learning Research"},{"key":"1852_CR80","doi-asserted-by":"crossref","unstructured":"Wang, W., Bao, H., Dong, L., Bjorck, J., Peng, Z., Liu, Q., Aggarwal, K., Khan, O., Singhal, S., Som, S., & Wei, F. (2023). Image as a foreign language: Beit pretraining for all vision and vision-language tasks.","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"1852_CR81","doi-asserted-by":"crossref","unstructured":"Wang, L., Liang, F., Li, Y., Ouyang, W., Zhang, H., & Shao, J. (2022). Repre: Improving self-supervised vision transformer with reconstructive pre-training. arXiv:2201.06857","DOI":"10.24963\/ijcai.2022\/200"},{"key":"1852_CR82","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, R., Shen, C., Kong, T., & Li, L. (2021). Dense contrastive learning for self-supervised visual pre-training. In CVPR (pp. 3024\u20133033).","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"1852_CR83","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.-Y., Yuille, A., & Feichtenhofer, C. (2021). Masked feature prediction for self-supervised visual pre-training. arXiv:2112.09133","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"1852_CR84","doi-asserted-by":"crossref","unstructured":"Wei, L., Xie, L., Zhou, W., Li, H., & Tian, Q. (2022). Mvp: Multimodality-guided visual pre-training. In ECCV.","DOI":"10.1007\/978-3-031-20056-4_20"},{"key":"1852_CR85","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.\u00a0X., & Lin, D. (2018). Unsupervised feature learning via non-parametric instance discrimination. In CVPR (pp. 3733\u20133742).","DOI":"10.1109\/CVPR.2018.00393"},{"key":"1852_CR86","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018). Unified perceptual parsing for scene understanding. In ECCV (pp. 418\u2013434).","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"1852_CR87","doi-asserted-by":"crossref","unstructured":"Xie, Z., Geng, Z., Hu, J., Zhang, Z., Hu, H., & Cao, Y. (2022). Revealing the dark secrets of masked image modeling. arXiv:2205.13543.","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"1852_CR88","unstructured":"Xie, J., Girshick, R., & Farhadi, A. (2016). Unsupervised deep embedding for clustering analysis. In ICML (pp. 478\u2013487). PMLR."},{"key":"1852_CR89","unstructured":"Xie, J., Li, W., Zhan, X., Liu, Z., Ong, Y. S., & Loy, C. C. (2022). Masked frequency modeling for self-supervised visual pre-training. arXiv:2206.07706"},{"key":"1852_CR90","doi-asserted-by":"crossref","unstructured":"Xie, Z., Lin, Y., Zhang, Z., Cao, Y., Lin, Stephen, & Hu, H. (2021). Propagate yourself: Exploring pixel-level consistency for unsupervised visual representation learning. In CVPR (pp. 16684\u201316693).","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"1852_CR91","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., & Hu, H. (2021). Simmim: A simple framework for masked image modeling. arXiv:2111.09886","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"1852_CR92","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Wei, Y., Dai, Q., & Hu, H. (2022). On data scaling in masked image modeling. arXiv:2206.04664","DOI":"10.1109\/CVPR52729.2023.00999"},{"key":"1852_CR93","doi-asserted-by":"crossref","unstructured":"Yang, J., Parikh, D., & Batra, D. (2016). Joint unsupervised learning of deep representations and image clusters. In CVPR (pp. 5147\u20135156).","DOI":"10.1109\/CVPR.2016.556"},{"key":"1852_CR94","unstructured":"Yi, K., Ge, Y., Li, Xiaotong, Y., Shusheng, L., Dian, W., Jianping, S. Y., & Qie, X. (2022). Masked image modeling with denoising contrast. arXiv:2205.09616"},{"key":"1852_CR95","unstructured":"You, Y., Gitman, I., & Ginsburg, B. (2017). Large batch training of convolutional networks. arXiv:1708.03888"},{"key":"1852_CR96","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.\u00a0J., Chun, S., Choe, J., & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV (pp. 6023\u20136032).","DOI":"10.1109\/ICCV.2019.00612"},{"key":"1852_CR97","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., & Deny, S. (2021). Barlow twins: Self-supervised learning via redundancy reduction. arXiv:2103.03230"},{"key":"1852_CR98","unstructured":"Zhang, X., Chen, J., Yuan, J., Chen, Q., Wang, J., Wang, X., Han, S., Chen, X., Pi, J., Yao, K., Han, J., Ding, E., & Wang, J. (2022). CAE v2: Context autoencoder with CLIP target. CoRRarxiv:2211.09799."},{"key":"1852_CR99","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. In ICLR.","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"1852_CR100","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., & Efros, A. A. (2016). Colorful image colorization. In ECCV (pp. 649\u2013666). Springer.","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"1852_CR101","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Hang, S., Zhu, J., Ni, L. M., & Shum, H.-Y. (2023). Dino: Detr with improved denoising anchor boxes for end-to-end object detection."},{"key":"1852_CR102","unstructured":"Zhang, X., Tian, Y., Huang, W., Ye, Q., Dai, Q., Xie, L., & Tian, Q. (2022). Hivit: Hierarchical vision transformer meets masked image modeling. arXiv:2205.14949"},{"key":"1852_CR103","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., & Kong, T. (2021). Ibot: Image bert pre-training with online tokenizer. arxiv:2111.07832"},{"key":"1852_CR104","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralb, A.(2017). Scene parsing through ade20k dataset. In CVPR (pp. 633\u2013641).","DOI":"10.1109\/CVPR.2017.544"},{"key":"1852_CR105","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Zhai, A. L., & Yamins, D. (2019). Local aggregation for unsupervised learning of visual embeddings. In ICCV (pp. 6002\u20136012).","DOI":"10.1109\/ICCV.2019.00610"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01852-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01852-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01852-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T03:11:49Z","timestamp":1705893109000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01852-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,28]]},"references-count":105,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["1852"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01852-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,28]]},"assertion":[{"value":"27 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}