{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T01:55:58Z","timestamp":1785376558418,"version":"3.55.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263125","type":"print"},{"value":"9783031263132","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26313-2_32","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"524-540","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Vision Transformer Compression and\u00a0Architecture Exploration with\u00a0Efficient Embedding Space Search"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2921-3168","authenticated-orcid":false,"given":"Daeho","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9799-1773","authenticated-orcid":false,"given":"Jaeil","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"32_CR1","unstructured":"Ashok, A., Rhinehart, N., Beainy, F., Kitani, K.M.: N2n learning: network to network compression via policy gradient reinforcement learning. arXiv preprint arXiv:1709.06030 (2017)"},{"key":"32_CR2","doi-asserted-by":"publisher","first-page":"4688","DOI":"10.1109\/TSP.2020.3014611","volume":"68","author":"S Aziznejad","year":"2020","unstructured":"Aziznejad, S., Gupta, H., Campos, J., Unser, M.: Deep neural networks with trainable activations and controlled lipschitz constant. IEEE Trans. Signal Process. 68, 4688\u20134699 (2020)","journal-title":"IEEE Trans. Signal Process."},{"key":"32_CR3","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"32_CR4","unstructured":"Brochu, E., Cora, V.M., De Freitas, N.: A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv preprint arXiv:1012.2599 (2010)"},{"key":"32_CR5","unstructured":"Cao, S., Wang, X., Kitani, K.M.: Learnable embedding space for efficient neural architecture compression. arXiv preprint arXiv:1902.00383 (2019)"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Chen, M., Peng, H., Fu, J., Ling, H.: Autoformer: searching transformers for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12270\u201312280 (2021)","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"32_CR7","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":"32_CR8","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":"32_CR9","unstructured":"Dong, Y., Cordonnier, J.B., Loukas, A.: Attention is not all you need: pure attention loses rank doubly exponentially with depth. In: International Conference on Machine Learning, pp. 2793\u20132803. PMLR (2021)"},{"key":"32_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"32_CR11","unstructured":"Goyal, S., Choudhury, A.R., Raje, S., Chakaravarthy, V., Sabharwal, Y., Verma, A.: Power-bert: accelerating bert inference via progressive word-vector elimination. In: International Conference on Machine Learning, pp. 3690\u20133699. PMLR (2020)"},{"key":"32_CR12","unstructured":"Hardt, M., Recht, B., Singer, Y.: Train faster, generalize better: stability of stochastic gradient descent. In: International Conference on Machine Learning, pp. 1225\u20131234. PMLR (2016)"},{"key":"32_CR13","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":"32_CR14","doi-asserted-by":"crossref","unstructured":"He, Y., Lin, J., Liu, Z., Wang, H., Li, L.J., Han, S.: Amc: automl for model compression and acceleration on mobile devices. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 784\u2013800 (2018)","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"32_CR15","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":"32_CR16","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)"},{"issue":"4","key":"32_CR17","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., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"32_CR18","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":"32_CR19","first-page":"10396","volume":"33","author":"C Lyle","year":"2020","unstructured":"Lyle, C., Schut, L., Ru, R., Gal, Y., van der Wilk, M.: A bayesian perspective on training speed and model selection. Adv. Neural. Inf. Process. Syst. 33, 10396\u201310408 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR20","unstructured":"Ma, X., Huang, H., Wang, Y., Romano, S., Erfani, S., Bailey, J.: Normalized loss functions for deep learning with noisy labels. In: International Conference on Machine Learning, pp. 6543\u20136553. PMLR (2020)"},{"issue":"1","key":"32_CR21","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/BF00940509","volume":"70","author":"JB Mockus","year":"1991","unstructured":"Mockus, J.B., Mockus, L.J.: Bayesian approach to global optimization and application to multiobjective and constrained problems. J. Optim. Theory Appl. 70(1), 157\u2013172 (1991)","journal-title":"J. Optim. Theory Appl."},{"key":"32_CR22","first-page":"24898","volume":"34","author":"B Pan","year":"2021","unstructured":"Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., Oliva, A.: Ia-red$$^2$$\u202f: interpretability-aware redundancy reduction for vision transformers. Adv. Neural. Inf. Process. Syst. 34, 24898\u201324911 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 377\u2013386 (2021)","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"32_CR24","unstructured":"Ru, B., Lyle, C., Schut, L., Fil, M., van der Wilk, M., Gal, Y.: Speedy performance estimation for neural architecture search. arXiv preprint arXiv:2006.04492 (2020)"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Tang, Y., Han, K., Wang, Y., Xu, C., Guo, J., Xu, C., Tao, D.: Patch slimming for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12165\u201312174 (2022)","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"32_CR26","unstructured":"Tang, Y., et al.: Augmented shortcuts for vision transformers. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"32_CR27","first-page":"10936","volume":"33","author":"Y Tang","year":"2020","unstructured":"Tang, Y., et al.: Scop: scientific control for reliable neural network pruning. Adv. Neural. Inf. Process. Syst. 33, 10936\u201310947 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR28","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":"32_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Walch, F., Hazirbas, C., Leal-Taixe, L., Sattler, T., Hilsenbeck, S., Cremers, D.: Image-based localization using LSTMS for structured feature correlation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 627\u2013637 (2017)","DOI":"10.1109\/ICCV.2017.75"},{"issue":"1","key":"32_CR31","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/BF00229304","volume":"8","author":"G Wood","year":"1996","unstructured":"Wood, G., Zhang, B.: Estimation of the lipschitz constant of a function. J. Global Optim. 8(1), 91\u2013103 (1996)","journal-title":"J. Global Optim."},{"key":"32_CR32","unstructured":"Xiong, R., et al.: On layer normalization in the transformer architecture. In: International Conference on Machine Learning, pp. 10524\u201310533. PMLR (2020)"},{"key":"32_CR33","unstructured":"Yang, H., Yin, H., Molchanov, P., Li, H., Kautz, J.: Nvit: vision transformer compression and parameter redistribution. arXiv preprint arXiv:2110.04869 (2021)"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Yao, Z., Cao, Y., Lin, Y., Liu, Z., Zhang, Z., Hu, H.: Leveraging batch normalization for vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 413\u2013422 (2021)","DOI":"10.1109\/ICCVW54120.2021.00050"},{"key":"32_CR35","unstructured":"Yu, S., et al.: Unified visual transformer compression. arXiv preprint arXiv:2203.08243 (2022)"},{"key":"32_CR36","unstructured":"Zhu, M., Tang, Y., Han, K.: Vision transformer pruning. arXiv preprint arXiv:2104.08500 (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26313-2_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:15:32Z","timestamp":1677658532000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26313-2_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263125","9783031263132"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26313-2_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}