{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:20:28Z","timestamp":1771698028259,"version":"3.50.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031023743","type":"print"},{"value":"9783031023750","type":"electronic"}],"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\/978-3-031-02375-0_4","type":"book-chapter","created":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:03:10Z","timestamp":1652180590000},"page":"47-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["NASformer: Neural Architecture Search for\u00a0Vision Transformer"],"prefix":"10.1007","author":[{"given":"Bolin","family":"Ni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaofeng","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,11]]},"reference":[{"key":"4_CR1","unstructured":"Bender, G., Kindermans, P.J., Zoph, B., Vasudevan, V., Le, Q.: Understanding and simplifying one-shot architecture search. In: ICML (2018)"},{"key":"4_CR2","unstructured":"Brock, A., Lim, T., Ritchie, J.M., Weston, N.: Smash: one-shot model architecture search through hypernetworks. In: ICLR (2018)"},{"key":"4_CR3","unstructured":"Chen, C.F., Panda, R., Fan, Q.: Regionvit: regional-to-local attention for vision transformers. arXiv preprint arXiv:2106.02689 (2021)"},{"key":"4_CR4","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, L., Wu, J., Tian, Q.: Progressive differentiable architecture search: bridging the depth gap between search and evaluation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00138"},{"key":"4_CR6","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. arXiv preprint arXiv:2104.13840 (2021)"},{"key":"4_CR7","unstructured":"Chu, X., et al.: Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)"},{"key":"4_CR8","unstructured":"Contributors, M.: MMSegmentation: openmmlab semantic segmentation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation (2020)"},{"key":"4_CR9","unstructured":"Contributors, O.: Open neural network exchange (2020). https:\/\/github.com\/onnx\/onnx"},{"key":"4_CR10","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., Yang, Y.: Searching for a robust neural architecture in four GPU hours. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00186"},{"key":"4_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Guo, Z., et al.: Single path one-shot neural architecture search with uniform sampling. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"4_CR15","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. arXiv preprint arXiv:2103.00112 (2021)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. arXiv preprint arXiv:2103.16302 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3464\u20133473 (2019)","DOI":"10.1109\/ICCV.2019.00356"},{"issue":"1\/2","key":"4_CR20","doi-asserted-by":"publisher","first-page":"81","DOI":"10.2307\/2332226","volume":"30","author":"MG Kendall","year":"1938","unstructured":"Kendall, M.G.: A new measure of rank correlation. Biometrika 30(1\/2), 81\u201393 (1938)","journal-title":"Biometrika"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Bossnas: exploring hybrid CNN-transformers with block-wisely self-supervised neural architecture search. arXiv preprint arXiv:2103.12424 (2021)","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"4_CR22","unstructured":"Li, L., Talwalkar, A.: Random search and reproducibility for neural architecture search. In: UAI (2019)"},{"key":"4_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"4_CR24","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: ICLR (2019)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"4_CR27","unstructured":"Luo, R., Tian, F., Qin, T., Chen, E., Liu, T.Y.: Neural architecture optimization. In: NeurIPS (2018)"},{"key":"4_CR28","unstructured":"Pham, H., Guan, M., Zoph, B., Le, Q., Dean, J.: Efficient neural architecture search via parameters sharing. In: ICML (2018)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"4_CR30","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. arXiv preprint arXiv:1906.05909 (2019)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"4_CR32","unstructured":"So, D., Le, Q., Liang, C.: The evolved transformer. In: International Conference on Machine Learning. PMLR (2019)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. arXiv preprint arXiv:2101.11605 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"4_CR34","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u2019egou, H.: Training data-efficient image transformers and distillation through attention. arXiv preprint arXiv:2012.12877 (2020)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. arXiv preprint arXiv:2103.17239 (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B., Shlens, J.: Scaling local self-attention for parameter efficient visual backbones. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12894\u201312904 (2021)","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"4_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1580"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., Wu, Z., Liu, Z., Cai, H., Zhu, L., Gan, C., Han, S.: Hat: Hardware-aware transformers for efficient natural language processing. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"4_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58548-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.-C.: Axial-deepLab: stand-alone axial-attention for panoptic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 108\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_7"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv preprint arXiv:2102.12122 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"3\u20134","key":"4_CR42","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992). https:\/\/doi.org\/10.1007\/BF00992696","journal-title":"Mach. Learn."},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Cars: continuous evolution for efficient neural architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1829\u20131838 (2020)","DOI":"10.1109\/CVPR42600.2020.00190"},{"key":"4_CR45","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token VIT: training vision transformers from scratch on imagenet. arXiv preprint arXiv:2101.11986 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, L., Hou, Q., Jiang, Z., Feng, J., Yan, S.: Volo: vision outlooker for visual recognition (2021)","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"4_CR48","unstructured":"Zhang, Q., Yang, Y.: Rest: an efficient transformer for visual recognition. arXiv preprint arXiv:2105.13677 (2021)"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"4_CR50","unstructured":"Zhou, D., et al.: Deepvit: towards deeper vision transformer. arXiv preprint arXiv:2103.11886 (2021)"},{"key":"4_CR51","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: ICLR (2016)"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-02375-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,4]],"date-time":"2023-02-04T20:29:35Z","timestamp":1675542575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-02375-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031023743","9783031023750"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-02375-0_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.acpr2021.org","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","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":"85","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":"55% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}