{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:40:30Z","timestamp":1743000030733,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785049"},{"type":"electronic","value":"9789819785056"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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\/978-981-97-8505-6_3","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:02:22Z","timestamp":1730930542000},"page":"32-46","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Swelling-ViT: Rethink Data-Efficient Vision Transformer from\u00a0Locality"],"prefix":"10.1007","author":[{"given":"Chuanrui","family":"Hu","sequence":"first","affiliation":[]},{"given":"Bin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Fudong","family":"Nian","sequence":"additional","affiliation":[]},{"given":"Jiaxin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Teng","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"3_CR1","unstructured":"Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image transformers (2021)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y.H., Yu, H., Wu, J.: Training vision transformers with only 2040 images. In: European Conference on Computer Vision, pp. 220\u2013237. Springer (2022)","DOI":"10.1007\/978-3-031-19806-9_13"},{"key":"3_CR3","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: Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2018)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31x31: Revisiting large kernel design in cnns. In: Computer Vision and Pattern Recognition, pp. 11963\u201311975 (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"3_CR6","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.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"3_CR7","unstructured":"Gani, H., Naseer, M., Yaqub, M.: How to train vision transformer on small-scale datasets? In: 33rd British machine vision conference 2022, BMVC 2022, London, UK, November 21\u201324, 2022. BMVA Press (2022), https:\/\/bmvc2022.mpi-inf.mpg.de\/0731.pdf"},{"key":"3_CR8","unstructured":"Hassani, A., Walton, S., Shah, N., Abuduweili, A., Li, J., Shi, H.: Escaping the big data paradigm with compact transformers. arXiv: Computer Vision and Pattern Recognition (2021)"},{"key":"3_CR9","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: Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR11","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)"},{"key":"3_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems (2012)"},{"key":"3_CR13","doi-asserted-by":"publisher","first-page":"123212","DOI":"10.1109\/ACCESS.2022.3224044","volume":"10","author":"S Lee","year":"2022","unstructured":"Lee, S., Lee, S., Song, B.C.: Improving vision transformers to learn small-size dataset from scratch. IEEE Access 10, 123212\u2013123224 (2022)","journal-title":"IEEE Access"},{"key":"3_CR14","first-page":"23818","volume":"34","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sangineto, E., Bi, W., Sebe, N., Lepri, B., Nadai, M.: Efficient training of visual transformers with small datasets. Adv. Neural. Inf. Process. Syst. 34, 23818\u201323830 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR15","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. International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"3_CR17","first-page":"14663","volume":"35","author":"Z Lu","year":"2022","unstructured":"Lu, Z., Xie, H., Liu, C., Zhang, Y.: Bridging the gap between vision transformers and convolutional neural networks on small datasets. Adv. Neural. Inf. Process. Syst. 35, 14663\u201314677 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR18","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)"},{"key":"3_CR19","unstructured":"Pouransari, H., Ghili, S.: Tiny imagenet visual recognition challenge (2014)"},{"key":"3_CR20","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training. arXiv (2018)"},{"key":"3_CR21","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"3_CR22","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. (2019)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"3_CR24","unstructured":"Tan, M., Le, Q.V.: EfficientNet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (2019)"},{"key":"3_CR25","unstructured":"Team, T.T.: Flowers (2019), http:\/\/download.tensorflow.org\/example_images\/flower_photos.tgz"},{"key":"3_CR26","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 (2021)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., J\u00e9gou, H.: Deit iii: Revenge of the vit. In: European Conference on Computer Vision, pp. 516\u2013533. Springer (2022)","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B.A., Shlens, J.: Scaling local self-attention for parameter efficient visual backbones. In: Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"3_CR29","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. Neural Information Processing Systems (2017)"},{"issue":"1","key":"3_CR30","doi-asserted-by":"publisher","first-page":"9535","DOI":"10.1038\/s41598-023-36724-x","volume":"13","author":"W Wang","year":"2023","unstructured":"Wang, W., Li, S., Shao, J., Jumahong, H.: Lkc-net: large kernel convolution object detection network. Sci. Rep. 13(1), 9535 (2023)","journal-title":"Sci. Rep."},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Wu, K., Peng, H., Chen, M., Fu, J., Chao, H.: Rethinking and improving relative position encoding for vision transformer. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, H., Zhao, L., Chen, T., Arik, S.\u00d6., Pfister, T.: Nested hierarchical transformer: Towards accurate, data-efficient and interpretable visual understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 3417\u20133425 (2022)","DOI":"10.1609\/aaai.v36i3.20252"},{"issue":"1","key":"3_CR33","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2020","unstructured":"Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., He, Q.: A comprehensive survey on transfer learning. Proc. IEEE 109(1), 43\u201376 (2020)","journal-title":"Proc. IEEE"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8505-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:03:54Z","timestamp":1730930634000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8505-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819785049","9789819785056"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8505-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}