{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T15:17:08Z","timestamp":1793805428555,"version":"4.6.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T00:00:00Z","timestamp":1690675200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T00:00:00Z","timestamp":1690675200000},"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":["Vis Comput"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s00371-023-02939-2","type":"journal-article","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T04:01:35Z","timestamp":1690689695000},"page":"2589-2598","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["A data efficient transformer based on Swin Transformer"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7434-8099","authenticated-orcid":false,"given":"Dazhi","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxue","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,30]]},"reference":[{"key":"2939_CR1","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2939_CR2","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778(2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2939_CR3","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: The International Conference on Machine Learning, pp. 6105\u20136114 (2019)"},{"key":"2939_CR4","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2015)"},{"key":"2939_CR5","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2939_CR6","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van, L., Maaten, D., Weinberger, K, Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"issue":"4","key":"2939_CR7","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y Lecun","year":"1989","unstructured":"Lecun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"issue":"11","key":"2939_CR8","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"2939_CR9","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"2939_CR10","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2939_CR11","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)"},{"key":"2939_CR12","first-page":"5998","volume":"30","author":"Attention is all you need","year":"2017","unstructured":"Attention is all you need: Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A, N., Kaiser, L., Polosukhin, I. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2939_CR13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"2939_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2939_CR15","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D. P., Song, K., Liang, D., Shao, L.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"2939_CR16","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357 (2020)"},{"key":"2939_CR17","first-page":"13937","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: Dynamicvit: efficient vision transformers with dynamic token sparsification. Adv. Neural Inf. Process. Syst. 34, 13937\u201313949 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2939_CR18","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: Cvt: Introducing convolutions to vision transformers. arXiv preprint arXiv:2103.15808 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"2939_CR19","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. Adv. Neural Inf. Process. Syst. 34, 15908\u201315919 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2939_CR20","unstructured":"Zhang, Z., Zhang, H., Zhao, L., Chen, T., Pfister, T.: Aggregating nested transformer. arXiv preprint arXiv:2105.12723 (2021)"},{"key":"2939_CR21","first-page":"15475","volume":"34","author":"Q Zhang","year":"2021","unstructured":"Zhang, Q., Yang, Y.B.: Rest: an efficient transformer for visual recognition. Adv Neural Inf. Process. Syst. 34, 15475\u201315485 (2021)","journal-title":"Adv Neural Inf. Process. Syst."},{"key":"2939_CR22","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z. H., Yan, S., et al.: Tokens-to-token vit: training vision transformers from scratch on imagenet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"2939_CR23","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 32\u201342 (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"2939_CR24","unstructured":"Hassani, A., Walton, S., Shah, N., Abuduweili, A., Li, J., Shi. H.: Escaping the big data paradigm with compact transformers. arXiv preprint arXiv:2104.05704 (2021)"},{"key":"2939_CR25","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"2939_CR26","unstructured":"Beltagy, I., Peters, M, E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"2939_CR27","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Toronto, ON, Canada (2009)"},{"key":"2939_CR28","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2939_CR29","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"2939_CR30","unstructured":"Ba, J. L., Kiros, J. R., Hinton, G.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"2939_CR31","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 843\u2013852 (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"2939_CR32","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S. J.: Rethinking spatial dimensions of vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11936\u201311945 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"2939_CR33","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 579\u2013588 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"2939_CR34","first-page":"24261","volume":"34","author":"IO Tolstikhin","year":"2021","unstructured":"Tolstikhin, I.O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Dosovitskiy, A.: Mlp-mixer: an all-mlp architecture for vision. Adv. Neural Inf. Process. Syst. 34, 24261\u201324272 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2939_CR35","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformers see better. arXiv preprint arXiv:2106.14881 (2021)"},{"key":"2939_CR36","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., et\u00a0al.: Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 8026 (2019)"},{"issue":"7","key":"2939_CR37","first-page":"3","volume":"7","author":"Y Le","year":"2015","unstructured":"Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)","journal-title":"CS 231N"},{"key":"2939_CR38","doi-asserted-by":"crossref","unstructured":"Cubuk, E, D., Zoph, B., Shlens, J., Le, Q, V.: Randaugment: Practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"2939_CR39","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization.arXiv preprint arXiv:1710.09412 (2018)"},{"key":"2939_CR40","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: IEEE International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2939_CR41","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: The National Conference on Artificial Intelligence, pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"2939_CR42","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K. Q.: Deep networks with stochastic depth. In: Europeon Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"2939_CR43","unstructured":"Kingma, D. P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv: 1412.6980 (2014)"},{"key":"2939_CR44","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)"},{"key":"2939_CR45","unstructured":"Nair, V., Hinton, G. E.: Rectified linear units improve restricted Boltzmann machines. In: The International Conference on Machine Learning (2010)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02939-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02939-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02939-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T13:12:43Z","timestamp":1712322763000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02939-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,30]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["2939"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02939-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,30]]},"assertion":[{"value":"28 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no conflict of interest or competing interests to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The source code used during the current study are available from","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}