{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:55:35Z","timestamp":1766138135744,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031212437"},{"type":"electronic","value":"9783031212444"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-21244-4_21","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T20:06:23Z","timestamp":1668110783000},"page":"274-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Attention-Based Token Pruning Method for\u00a0Vision Transformers"],"prefix":"10.1007","author":[{"given":"Kaicheng","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaxiong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianzhong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"21_CR1","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"21_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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"21_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-030-58565-5_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Du","year":"2020","unstructured":"Du, R., et al.: Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 153\u2013168. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_10"},{"key":"21_CR6","unstructured":"Dubey, A., Gupta, O., Raskar, R., Naik, N.: Maximum-entropy fine grained classification. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Gao, Y., Han, X., Wang, X., Huang, W., Scott, M.: Channel interaction networks for fine-grained image categorization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10818\u201310825 (2020)","DOI":"10.1609\/aaai.v34i07.6712"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Ge, W., Lin, X., Yu, Y.: Weakly supervised complementary parts models for fine-grained image classification from the bottom up. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3034\u20133043 (2019)","DOI":"10.1109\/CVPR.2019.00315"},{"key":"21_CR9","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Guo, Q., Qiu, X., Liu, P., Shao, Y., Xue, X., Zhang, Z.: Star-transformer. arXiv preprint arXiv:1902.09113 (2019)","DOI":"10.18653\/v1\/N19-1133"},{"key":"21_CR11","unstructured":"He, J., et al.: Transfg: a transformer architecture for fine-grained recognition. arXiv preprint arXiv:2103.07976 (2021)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1389\u20131397 (2017)","DOI":"10.1109\/ICCV.2017.155"},{"key":"21_CR14","unstructured":"Jiang, Z., et al.: Token labeling: Training a 85.4% top-1 accuracy vision transformer with 56m parameters on imagenet. arXiv e-prints pp. arXiv-2104 (2021)"},{"key":"21_CR15","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are rnns: fast autoregressive transformers with linear attention. In: International Conference on Machine Learning, pp. 5156\u20135165. PMLR (2020)"},{"key":"21_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Liu, C., Xie, H., Zha, Z.J., Ma, L., Yu, L., Zhang, Y.: Filtration and distillation: enhancing region attention for fine-grained visual categorization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11555\u201311562 (2020)","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: 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":"21_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2736\u20132744 (2017)","DOI":"10.1109\/ICCV.2017.298"},{"key":"21_CR20","unstructured":"Loshchilov, I., Hutter, F.: Sgdr: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"21_CR21","unstructured":"Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., Oliva, A.: Ia-red: interpretability-aware redundancy reduction for vision transformers. Adv. Neural Inf. Process. Syst. 34 (2021)"},{"key":"21_CR22","unstructured":"Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055\u20134064. PMLR (2018)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"21_CR24","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 (2021)"},{"key":"21_CR25","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"21_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, pp. 10347\u201310357. PMLR (2021)"},{"key":"21_CR27","unstructured":"Vaswani, A., Set al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"21_CR28","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"21_CR29","unstructured":"Wang, J., Yu, X., Gao, Y.: Feature fusion vision transformer for fine-grained visual categorization. arXiv preprint arXiv:2107.02341 (2021)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, Y., Gong, Y., Zhang, J., Zheng, N.: Grassmann pooling as compact homogeneous bilinear pooling for fine-grained visual classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 355\u2013370 (2018)","DOI":"10.1007\/978-3-030-01219-9_22"},{"key":"21_CR31","unstructured":"Yang, S., Liu, S., Yang, C., Wang, C.: Re-rank coarse classification with local region enhanced features for fine-grained image recognition. arXiv preprint arXiv:2102.09875 (2021)"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Yue, X., et al.: Vision transformer with progressive sampling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 387\u2013396 (2021)","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"21_CR33","first-page":"17283","volume":"33","author":"M Zaheer","year":"2020","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. Adv. Neural Inf. Process. Syst. 33, 17283\u201317297 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"21_CR34","unstructured":"Zheng, H., Fu, J., Zha, Z.J., Luo, J.: Learning deep bilinear transformation for fine-grained image representation. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"21_CR35","unstructured":"Zhu, M., Han, K., Tang, Y., Wang, Y.: Visual transformer pruning. arXiv e-prints pp. arXiv-2104 (2021)"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Zhuang, P., Wang, Y., Qiao, Y.: Learning attentive pairwise interaction for fine-grained classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13130\u201313137 (2020)","DOI":"10.1609\/aaai.v34i07.7016"}],"container-title":["Lecture Notes in Computer Science","Rough Sets"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21244-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T17:06:51Z","timestamp":1709831211000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21244-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031212437","9783031212444"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21244-4_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IJCRS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Rough Sets","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Suzhou","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ijcrs2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ijcrs2022.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"42","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}