{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T01:51:52Z","timestamp":1783734712921,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"8-9","license":[{"start":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T00:00:00Z","timestamp":1591833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T00:00:00Z","timestamp":1591833600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s11263-020-01339-6","type":"journal-article","created":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T11:02:56Z","timestamp":1591873376000},"page":"2035-2048","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Hardware-Centric AutoML for Mixed-Precision Quantization"],"prefix":"10.1007","volume":"128","author":[{"given":"Kuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-7618","authenticated-orcid":false,"given":"Song","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,6,11]]},"reference":[{"key":"1339_CR1","unstructured":"Apple. (2018). Apple describes 7nm A12 bionic chips. http:\/\/www.eenewsanalog.com\/news\/apple-describes-7nm-a12-bionic-chip\/page\/0\/1."},{"key":"1339_CR2","unstructured":"Cai, H., Yang, J., Zhang, W., Han, S., & Yu, Y. (2018). Path-level network transformation for efficient architecture search. In ICML."},{"key":"1339_CR3","unstructured":"Cai, H., Zhu, L., & Han, S. (2019). ProxylessNAS: Direct neural architecture search on target task and hardware. In ICLR."},{"key":"1339_CR4","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P. I. J., Srinivasan, V., & Gopalakrishnan, K. (2018). PACT: Parameterized clipping activation for quantized neural networks. arXiv."},{"key":"1339_CR5","doi-asserted-by":"crossref","unstructured":"Chollet F. (2017). Xception\u2014Deep learning with depthwise separable convolutions. In CVPR.","DOI":"10.1109\/CVPR.2017.195"},{"key":"1339_CR6","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016). Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv."},{"key":"1339_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Li, F. F. (2009). ImageNet\u2014A large-scale hierarchical image database. In CVPR.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1339_CR8","unstructured":"Han, S. (2017). Efficient methods and hardware for deep learning. PhD thesis."},{"key":"1339_CR9","unstructured":"Han, S., Mao, H., & Dally, W. (2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In ICLR."},{"key":"1339_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1339_CR11","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., & Sun, J. (2017). Channel pruning for accelerating very deep neural networks. In ICCV.","DOI":"10.1109\/ICCV.2017.155"},{"key":"1339_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Lin, J., Liu, Z., Wang, H., Li, L. J., & Han S. (2018). AMC: AutoML for model compression and acceleration on mobile devices. In ECCV.","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"1339_CR13","unstructured":"Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., et al. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"1339_CR14","unstructured":"Imagination. (2018). Power vr neural network accelerator. https:\/\/www.imgtec.com\/vision-ai\/powervr-series2nx\/powervr-ax2145-nna\/."},{"key":"1339_CR15","doi-asserted-by":"crossref","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A.G., et al. (2018). Quantization and training of neural networks for efficient integer-arithmetic-only inference. In CVPR.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"1339_CR16","unstructured":"Kingma, D., & Ba, J. (2015). Adam\u2014A method for stochastic optimization. In ICLR."},{"key":"1339_CR17","unstructured":"Krishnamoorthi, R. (2018). Quantizing deep convolutional networks for efficient inference\u2014A whitepaper. arXiv."},{"key":"1339_CR18","unstructured":"Lillicrap, T., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., et al. (2016). Continuous control with deep reinforcement learning. In ICLR."},{"key":"1339_CR19","doi-asserted-by":"crossref","unstructured":"Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L. et al. (2018). Progressive neural architecture search. In ECCV.","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"1339_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G, Yan, S., & Zhang, C. (2017). Learning efficient convolutional networks through network slimming. In ICCV.","DOI":"10.1109\/ICCV.2017.298"},{"key":"1339_CR21","unstructured":"Nvidia. (2018). Nvidia tensor cores. https:\/\/www.nvidia.com\/en-us\/data-center\/tensorcore\/."},{"key":"1339_CR22","unstructured":"Pham, H., Guan, M. Y., Zoph, B., Le, Q. V., & Dean, J. (2018). Efficient neural architecture search via parameter sharing. In ICML."},{"key":"1339_CR23","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016). XNOR-Net\u2014ImageNet classification using binary convolutional neural networks. In ECCV.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"1339_CR24","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In CVPR.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1339_CR25","doi-asserted-by":"crossref","unstructured":"Sharma, H., Park, J., Suda, N., Lai, L., Chau, B., Chandra, V., et al. (2018). Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network. In ISCA.","DOI":"10.1109\/ISCA.2018.00069"},{"key":"1339_CR26","doi-asserted-by":"crossref","unstructured":"Umuroglu, Y., Rasnayake, L., & Sjalander, M., (2018). Bismo: A scalable bit-serial matrix multiplication overlay for reconfigurable computing. In FPL.","DOI":"10.1109\/FPL.2018.00059"},{"issue":"4","key":"1339_CR27","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., & Patterson, D. (2009). Roofline: an insightful visual performance model for multicore architectures. Communications of the ACM, 52(4), 65\u201376.","journal-title":"Communications of the ACM"},{"key":"1339_CR28","unstructured":"Xilinx. (2018a). Ultrascale architecture and product data sheet: Overview. https:\/\/www.xilinx.com\/support\/documentation\/data_sheets\/ds890-ultrascale-overview.pdf."},{"key":"1339_CR29","unstructured":"Xilinx (2018b). Zynq-7000 soc data sheet: Overview. https:\/\/www.xilinx.com\/support\/documentation\/data_sheets\/ds190-Zynq-7000-Overview.pdf."},{"key":"1339_CR30","doi-asserted-by":"crossref","unstructured":"Yang, T. J., Chen, Y. H., & Sze, V. (2016). Designing energy-efficient convolutional neural networks using energy-aware pruning. arXiv.","DOI":"10.1109\/CVPR.2017.643"},{"key":"1339_CR31","doi-asserted-by":"crossref","unstructured":"Yang, T. J., Howard, A., Chen, B., Zhang, X., Go, A., Sandler, M., et al. (2018). Netadapt: Platform-aware neural network adaptation for mobile applications. In ECCV.","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"1339_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, A., Yao, A., Wang, K., & Chen Y. (2018). Explicit loss-error-aware quantization for low-bit deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 9426\u20139435).","DOI":"10.1109\/CVPR.2018.00982"},{"key":"1339_CR33","unstructured":"Zhou, S., Ni, Z., Zhou, X., Wen, H., Wu, Y., & Zou, Y. (2016). DoReFa-Net\u2014Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. arXiv."},{"key":"1339_CR34","unstructured":"Zhu, C., Han, S., Mao, H., & Dally, W. (2017). Trained ternary quantization. In ICLR."},{"key":"1339_CR35","unstructured":"Zoph, B., & Le, Q. V. (2017). Neural architecture search with reinforcement learning. In ICLR."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01339-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01339-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01339-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T23:29:50Z","timestamp":1623367790000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01339-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,11]]},"references-count":35,"journal-issue":{"issue":"8-9","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["1339"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01339-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,11]]},"assertion":[{"value":"20 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}