{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:38:42Z","timestamp":1786635522833,"version":"3.56.0"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736605","type":"print"},{"value":"9783031736612","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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\/978-3-031-73661-2_5","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T11:09:04Z","timestamp":1731150544000},"page":"78-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":554,"title":["MobileNetV4: Universal Models for\u00a0the\u00a0Mobile Ecosystem"],"prefix":"10.1007","author":[{"given":"Danfeng","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chas","family":"Leichner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manolis","family":"Delakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Fornoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shixin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colby","family":"Banbury","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxi","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Berkin","family":"Akin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaibhav","family":"Aggarwal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tenghui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Moro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Howard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Akin, B., et al.: Searching for efficient neural architectures for on-device ML on edge TPUs. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2022, New Orleans, LA, USA, 19\u201320 June 2022, pp. 2666\u20132675. IEEE (2022)","DOI":"10.1109\/CVPRW56347.2022.00300"},{"key":"5_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"5_CR3","first-page":"22614","volume":"34","author":"I Bello","year":"2021","unstructured":"Bello, I., et al.: Revisiting ResNets: improved training and scaling strategies. Adv. Neural. Inf. Process. Syst. 34, 22614\u201322627 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Bender, G., et al.: Can weight sharing outperform random architecture search? An investigation with tunas. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01433"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Beyer, L., Zhai, X., Royer, A., Markeeva, L., Anil, R., Kolesnikov, A.: Knowledge distillation: a good teacher is patient and consistent. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10925\u201310934 (2022)","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"5_CR6","unstructured":"Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791 (2019)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-former: bridging MobileNet and transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5270\u20135279 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"5_CR8","unstructured":"Chowdhery, A., et\u00a0al.: PaLM: scaling language modeling with pathways. arXiv preprint\u00a0arXiv:2204.02311 (2022)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Chu, G., et al.: Discovering multi-hardware mobile models via architecture search. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2021, Virtual, 19\u201325 June 2021, pp. 3022\u20133031. Computer Vision Foundation\/IEEE (2021)","DOI":"10.1109\/CVPRW53098.2021.00337"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: RandAugment: practical automated data augmentation with a reduced search space. In: Larochelle, H., Ranzato, M.A., Hadsell, R., Balcan, M.-F., Lin, H.-T. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6\u201312 December 2020, Virtual (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., 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 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Cai, H., et al.: EfficientViT: lightweight multi-scale attention for high-resolution dense prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Liu, X., et al. EfficientViT: memory efficient vision transformer with cascaded group attention. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: CMT: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: GhostNet: more features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"5_CR18","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"5_CR19","unstructured":"Du, X., et al.: TensorFlow model garden (2020). https:\/\/github.com\/tensorflow\/models"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetv3. CoRR, abs\/1905.02244 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"5_CR21","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR, abs\/1704.04861 (2017)"},{"key":"5_CR22","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"5_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"5_CR25","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp. 448\u2013456. PMLR (2015)"},{"key":"5_CR26","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR), San Diega, CA, USA (2015)"},{"key":"5_CR27","unstructured":"Lee, A.N., Hunter, C.J., Rui, N.: Platypus: quick, cheap, and powerful refinement of LLMs. arXiv preprint arXiv:2308.07317 (2023)"},{"key":"5_CR28","unstructured":"Li, J., et al.: Next-ViT: next generation vision transformer for efficient deployment in realistic industrial scenarios. arXiv preprint arXiv:2207.05501 (2022)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Rethinking vision transformers for MobileNet size and speed. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16889\u201316900 (2023)","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"5_CR30","unstructured":"Li, Y., et al.: EfficientFormer: vision transformers at MobileNet speed. In: NeurIPS (2022)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 936\u2013944. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22\u201329 October 2017, pp. 2999\u20133007. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"5_CR33","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":"5_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 11966\u201311976. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"5_CR35","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)"},{"key":"5_CR36","unstructured":"Mehta, S., Rastegari, M.: Separable self-attention for mobile vision transformers. arXiv preprint arXiv:2206.02680 (2022)"},{"key":"5_CR37","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807\u2013814 (2010)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.-C.: MobileNetv2: inverted residuals and linear bottlenecks. CoRR, abs\/1801.04381 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"5_CR39","unstructured":"Shazeer, N.: Fast transformer decoding: one write-head is all you need. arXiv preprint arXiv:1911.02150 (2019)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 843\u2013852 (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"5_CR42","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Le, Q.V.: MnasNet: platform-aware neural architecture search for mobile. CoRR, abs\/1807.11626 (2018)"},{"key":"5_CR43","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":"5_CR44","first-page":"9969","volume":"35","author":"Y Tang","year":"2022","unstructured":"Tang, Y., Han, K., Guo, J., Chang, X., Chao, X., Wang, Y.: GhostNetv2: enhance cheap operation with long-range attention. Adv. Neural. Inf. Process. Syst. 35, 9969\u20139982 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR45","unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., Tuzel, O., Ranjan, A.: FastViT: a fast hybrid vision transformer using structural reparameterization. arXiv preprint arXiv:2303.14189 (2023)"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., Tuzel, O., Ranjan, A.: MobileOne: an improved one millisecond mobile backbone. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7907\u20137917 (2023)","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"5_CR47","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"4","key":"5_CR49","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"5_CR50","unstructured":"Wu, B., et al.: FBNet: hardware-aware efficient convnet design via differentiable neural architecture search. CoRR, abs\/1812.03443 (2018)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.-T., Hovy, E., Le, Q.V.: Self-training with noisy student improves ImageNet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Yang, T.-J., et al.: NetAdapt: platform-aware neural network adaptation for mobile applications. CoRR, abs\/1804.03230 (2018)","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"5_CR54","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"5_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. CoRR, abs\/1707.01083 (2017)","DOI":"10.1109\/CVPR.2018.00716"}],"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\/978-3-031-73661-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T12:03:00Z","timestamp":1731153780000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73661-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031736605","9783031736612"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73661-2_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 November 2024","order":1,"name":"first_online","label":"First Online","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"}}]}}