{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:42:49Z","timestamp":1777653769914,"version":"3.51.4"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585389","type":"print"},{"value":"9783030585396","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58539-6_26","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:02:46Z","timestamp":1604689366000},"page":"430-446","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["PROFIT: A Novel Training Method for sub-4-bit MobileNet Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-9819","authenticated-orcid":false,"given":"Eunhyeok","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5853-0675","authenticated-orcid":false,"given":"Sungjoo","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Albericio, J., Judd, P., Hetherington, T.H., Aamodt, T.M., Jerger, N.D.E., Moshovos, A.: Cnvlutin: ineffectual-neuron-free deep neural network computing. In: International Symposium on Computer Architecture (ISCA) (2016)","DOI":"10.1109\/ISCA.2016.11"},{"key":"26_CR2","unstructured":"Baskin, C., et al.: UNIQ: uniform noise injection for non-uniform quantization of neural networks. arXiv:1804.10969 (2018)"},{"key":"26_CR3","unstructured":"Choi, J., Chuang, P.I., Wang, Z., Venkataramani, S., Srinivasan, V., Gopalakrishnan, K.: Bridging the accuracy gap for 2-bit quantized neural networks. arXiv:1807.06964 (2018)"},{"key":"26_CR4","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I., Srinivasan, V., Gopalakrishnan, K.: PACT: parameterized clipping activation for quantized neural networks. arXiv:1805.06085 (2018)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Human Language Technologies (NAACL-HLT). North American Chapter of the Association for Computational Linguistics (2019)"},{"key":"26_CR7","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned step size quantization. arXiv:1902.08153) (2019)"},{"key":"26_CR8","unstructured":"Finkelstein, A., Almog, U., Grobman, M.: Fighting quantization bias with bias. arXiv:1906.03193 (2019)"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Gong, R., et al.: Differentiable soft quantization: bridging full-precision and low-bit neural networks. arXiv:1908.05033 (2019)","DOI":"10.1109\/ICCV.2019.00495"},{"key":"26_CR10","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour. arXiv:1706.02677 (2017)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR12","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv:1503.02531 (2015)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetV3. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"26_CR14","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)"},{"issue":"1","key":"26_CR15","first-page":"6869","volume":"18","author":"I Hubara","year":"2017","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Quantized neural networks: training neural networks with low precision weights and activations. J. Mach. Learn. Res. (JMLR) 18(1), 6869\u20136898 (2017)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"26_CR16","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D.P., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. In: Uncertainty in Artificial Intelligence (UAI) (2018)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Jung, S., et al.: Learning to quantize deep networks by optimizing quantization intervals with task loss. In: Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00448"},{"key":"26_CR18","unstructured":"Krishnamoorthi, R.: Quantizing deep convolutional networks for efficient inference: a whitepaper. arXiv:1806.08342 (2018)"},{"key":"26_CR19","unstructured":"Krizhevsky, A., Nair, V., Hinton, G.: The cifar-10 dataset (2014). https:\/\/www.cs.toronto.edu\/~kriz\/cifar.html. Accessed 03 Mar 2020"},{"key":"26_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Neural Information Processing Systems (NeurIPS) (2012)"},{"key":"26_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/978-3-030-01267-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Liu","year":"2018","unstructured":"Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.-T.: Bi-Real Net: enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 747\u2013763. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_44"},{"key":"26_CR22","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"26_CR23","unstructured":"Mishra, A.K., Nurvitadhi, E., Cook, J.J., Marr, D.: WRPN: wide reduced-precision networks. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Nagel, M., van Baalen, M., Blankevoort, T., Welling, M.: Data-free quantization through weight equalization and bias correction. arXiv:1906.04721 (2019)","DOI":"10.1109\/ICCV.2019.00141"},{"key":"26_CR25","unstructured":"INT4 precision for AI inference (2019). https:\/\/devblogs.nvidia.com\/int4-for-ai-inference\/. Accessed 03 Mar 2020"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Park, E., Kim, D., Yoo, S.: Energy-efficient neural network accelerator based on outlier-aware low-precision computation. In: International Symposium on Computer Architecture (ISCA) (2018)","DOI":"10.1109\/ISCA.2018.00063"},{"key":"26_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-46493-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Rastegari","year":"2016","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525\u2013542. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32"},{"key":"26_CR28","unstructured":"Samsung low-power NPU solution for AI deep learning (2019). https:\/\/news.samsung.com\/global\/samsung-electronics-introduces-a-high-speed-low-power-npu-solution-for-ai-deep-learning. Accessed 03 Mar 2020"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: MobileNetV2: inverted residuals and linear bottlenecks. In: Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Sharma, H., et al.: Bit fusion: bit-level dynamically composable architecture for accelerating deep neural networks. In: International Symposium on Computer Architecture (ISCA) (2018)","DOI":"10.1109\/ISCA.2018.00069"},{"key":"26_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"26_CR32","unstructured":"Snapdragon neural processing engine SDK (2017). https:\/\/developer.qualcomm.com\/docs\/snpe\/index.html. Accessed 03 Mar 2020"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Song, J., et al.: 7.1 an 11.5 TOPS\/W 1024-MAC butterfly structure dual-core sparsity-aware neural processing unit in 8nm flagship mobile SoS. In: International Solid-State Circuits Conference (ISSCC) (2019)","DOI":"10.1109\/ISSCC.2019.8662476"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile. In: Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"26_CR35","unstructured":"Tulloch, A., Jia, Y.: High performance ultra-low-precision convolutions on mobile devices. arXiv:1712.02427 (2017)"},{"key":"26_CR36","unstructured":"Tulloch, A., Jia, Y.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Wang, T., Xiong, J., Xu, X., Shi, Y.: SCNN: a general distribution based statistical convolutional neural network with application to video object detection. In: Association for the Advancement of Artificial Intelligence (AAAI) (2019)","DOI":"10.1609\/aaai.v33i01.33015321"},{"key":"26_CR38","unstructured":"Wu, H.: NVIDIA low precision inference on GPU. In: GPU Technology Conference (2019)"},{"key":"26_CR39","unstructured":"Zhou, S., Ni, Z., Zhou, X., Wen, H., Wu, Y., Zou, Y.: DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv:1606.06160 (2016)"},{"key":"26_CR40","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1007\/s11390-017-1750-y","volume":"32","author":"S Zhou","year":"2017","unstructured":"Zhou, S., Wang, Y., Wen, H., He, Q., Zou, Y.: Balanced quantization: an effective and efficient approach to quantized neural networks. J. Comput. Sci. Technol. 32, 667\u2013682 (2017). https:\/\/doi.org\/10.1007\/s11390-017-1750-y","journal-title":"J. Comput. Sci. Technol."},{"key":"26_CR41","unstructured":"Zhu, C., Han, S., Mao, H., Dally, W.J.: Trained ternary quantization. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Shen, C., Tan, M., Liu, L., Reid, I.D.: Towards effective low-bitwidth convolutional neural networks. In: Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00826"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58539-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:15:26Z","timestamp":1730852126000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58539-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585389","9783030585396"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58539-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","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":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}