{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:29:57Z","timestamp":1778171397548,"version":"3.51.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732089","type":"print"},{"value":"9783031732096","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73209-6_16","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"269-287","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["LPViT: Low-Power Semi-structured Pruning for\u00a0Vision Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7222-2628","authenticated-orcid":false,"given":"Kaixin","family":"Xu","sequence":"first","affiliation":[]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chunyun","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xue","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Min","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[]},{"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"16_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1007\/978-3-030-92659-5_34","volume-title":"Pattern Recognition","author":"A Amini","year":"2021","unstructured":"Amini, A., Periyasamy, A.S., Behnke, S.: T6D-direct: transformers for\u00a0multi-object 6d pose direct regression. In: Bauckhage, C., Gall, J., Schwing, A. (eds.) DAGM GCPR 2021. LNCS, vol. 13024, pp. 530\u2013544. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-92659-5_34"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Buluc, A., Gilbert, J.R.: Challenges and advances in parallel sparse matrix-matrix multiplication. In: 2008 37th International Conference on Parallel Processing, pp. 503\u2013510. IEEE (2008)","DOI":"10.1109\/ICPP.2008.45"},{"key":"16_CR3","first-page":"213","volume":"2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. Comput. Vis.-ECCV 2020, 213\u2013229 (2020)","journal-title":"Comput. Vis.-ECCV"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Li, L., Aly, M.M.S.: Vita: a highly efficient dataflow and architecture for vision transformers. In: 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), IEEE (2024)","DOI":"10.23919\/DATE58400.2024.10546565"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Pre-trained image processing transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299\u201312310 (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"16_CR6","first-page":"19974","volume":"34","author":"T Chen","year":"2021","unstructured":"Chen, T., Cheng, Y., Gan, Z., Yuan, L., Zhang, L., Wang, Z.: Chasing sparsity in vision transformers: an end-to-end exploration. Adv. Neural. Inf. Process. Syst. 34, 19974\u201319988 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR7","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"16_CR8","unstructured":"Cordonnier, J.B., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. In: International Conference on Learning Representations (2019)"},{"key":"16_CR9","unstructured":"Cordonnier, J.B., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=HJlnC1rKPB"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"16_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"16_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"16_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"16_CR14","unstructured":"Evci, U., Gale, T., Menick, J., Castro, P.S., Elsen, E.: Rigging the lottery: making all tickets winners. In: International Conference on Machine Learning, pp. 2943\u20132952. PMLR (2020)"},{"key":"16_CR15","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"16_CR16","unstructured":"Frankle, J., Dziugaite, G.K., Roy, D., Carbin, M.: Pruning neural networks at initialization: Why are we missing the mark? In: International Conference on Learning Representations (2020)"},{"key":"16_CR17","unstructured":"Gale, T., Elsen, E., Hooker, S.: The state of sparsity in deep neural networks. arXiv preprint arXiv:1902.09574 (2019)"},{"key":"16_CR18","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":"16_CR19","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)"},{"key":"16_CR20","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"16_CR21","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"16_CR22","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":"16_CR23","unstructured":"Isik, B., Weissman, T., No, A.: An information-theoretic justification for model pruning. In: International Conference on Artificial Intelligence and Statistics, pp. 3821\u20133846. PMLR (2022)"},{"issue":"7","key":"16_CR24","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1145\/3360307","volume":"63","author":"NP Jouppi","year":"2020","unstructured":"Jouppi, N.P., et al.: A domain-specific supercomputer for training deep neural networks. Commun. ACM 63(7), 67\u201378 (2020)","journal-title":"Commun. ACM"},{"key":"16_CR25","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: International Conference on Learning Representations (2019)"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via latency-aware soft token pruning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13671, pp. 620\u2013640. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_37","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"16_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Kurtic, E., et al.: The optimal bert surgeon: Scalable and accurate second-order pruning for large language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 4163\u20134181 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Lagunas, F., Charlaix, E., Sanh, V., Rush, A.M.: Block pruning for faster transformers. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 10619\u201310629 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"16_CR30","unstructured":"Lee, J., Park, S., Mo, S., Ahn, S., Shin, J.: Layer-adaptive sparsity for the magnitude-based pruning. In: International Conference on Learning Representations (2020)"},{"key":"16_CR31","unstructured":"Lee, N., Ajanthan, T., Torr, P.: Snip: single-shot network pruning based on connection sensitivity. In: International Conference on Learning Representations. Open Review (2019)"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Lin, M., et al.: Hrank: filter pruning using high-rank feature map. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1529\u20131538 (2020)","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Liu, J., Niu, L., Yuan, Z., Yang, D., Wang, X., Liu, W.: PD-quant: post-training quantization based on prediction difference metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24427\u201324437 (2023)","DOI":"10.1109\/CVPR52729.2023.02340"},{"key":"16_CR34","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":"16_CR35","doi-asserted-by":"crossref","unstructured":"Luo, J.H., Wu, J., Lin, W.: Thinet: a filter level pruning method for deep neural network compression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5058\u20135066 (2017)","DOI":"10.1109\/ICCV.2017.541"},{"issue":"3","key":"16_CR36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3446640","volume":"5","author":"J Mao","year":"2021","unstructured":"Mao, J., Yang, H., Li, A., Li, H., Chen, Y.: Tprune: Efficient transformer pruning for mobile devices. ACM Trans. Cyber-Phys. Syst. 5(3), 1\u201322 (2021)","journal-title":"ACM Trans. Cyber-Phys. Syst."},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11264\u201311272 (2019)","DOI":"10.1109\/CVPR.2019.01152"},{"key":"16_CR38","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. In: International Conference on Learning Representations (2016)"},{"key":"16_CR39","unstructured":"Morcos, A., Yu, H., Paganini, M., Tian, Y.: One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"16_CR40","first-page":"12894","volume":"35","author":"M Shen","year":"2022","unstructured":"Shen, M., Yin, H., Molchanov, P., Mao, L., Liu, J., Alvarez, J.M.: Structural pruning via latency-saliency knapsack. Adv. Neural. Inf. Process. Syst. 35, 12894\u201312908 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., Zhou, D.: Mobilebert: a compact task-agnostic bert for resource-limited devices. arXiv preprint arXiv:2004.02984 (2020)","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"16_CR42","unstructured":"Tang, Y., et al.: Scientific control for reliable neural network pruning. Neural Inf. Proc. Syst. (NeurIPS) 1(2), 7 (2020)"},{"key":"16_CR43","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":"16_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural Information Processing Systems, vol. 30 (2017)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, Z., Han, S.: Spatten: efficient sparse attention architecture with cascade token and head pruning. In: 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 97\u2013110. IEEE (2021)","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"16_CR46","doi-asserted-by":"publisher","unstructured":"Wang, Z., Lin, J., Geng, X., Aly, M.M.S., Chandrasekhar, V.: RDO-Q: Extremely fine-grained channel-wise quantization via rate-distortion optimization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13672, pp. 157\u2013172. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19775-8_10","DOI":"10.1007\/978-3-031-19775-8_10"},{"key":"16_CR47","unstructured":"Wu, Z., Liu, Z., Lin, J., Lin, Y., Han, S.: Lite transformer with long-short range attention. In: International Conference on Learning Representations (2019)"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Xu, K., Wang, Z., Geng, X., Wu, M., Li, X., Lin, W.: Efficient joint optimization of layer-adaptive weight pruning in deep neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17447\u201317457 (2023)","DOI":"10.1109\/ICCV51070.2023.01600"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Yang, H., Yin, H., Shen, M., Molchanov, P., Li, H., Kautz, J.: Global vision transformer pruning with hessian-aware saliency. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18547\u201318557 (2023)","DOI":"10.1109\/CVPR52729.2023.01779"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Yu, L., Xiang, W.: X-pruner: explainable pruning for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24355\u201324363 (2023)","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Yu, R., et al.: Nisp: pruning networks using neuron importance score propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9194\u20139203 (2018)","DOI":"10.1109\/CVPR.2018.00958"},{"key":"16_CR52","unstructured":"Yu, S., et al.: Unified visual transformer compression. In: International Conference on Learning Representations (2021)"},{"key":"16_CR53","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":"16_CR54","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Moosavi-Dezfooli, S.M., Cheung, N.M., Frossard, P.: Adaptive quantization for deep neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11623"},{"key":"16_CR56","unstructured":"Zhu, M.H., Gupta, S.: To prune, or not to prune: exploring the efficacy of pruning for model compression (2018)"},{"key":"16_CR57","unstructured":"Zhu, M., Tang, Y., Han, K.: Vision transformer pruning. arXiv preprint arXiv:2104.08500 (2021)"},{"key":"16_CR58","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke"}],"updated-by":[{"DOI":"10.1007\/978-3-031-73209-6_27","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T00:00:00Z","timestamp":1744070400000}}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73209-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T12:24:45Z","timestamp":1744115085000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73209-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732089","9783031732096"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73209-6_16","relation":{"correction":[{"id-type":"doi","id":"10.1007\/978-3-031-73209-6_27","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"8 April 2025","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A correction has been published.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}