{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:59:18Z","timestamp":1775815158085,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012243","type":"print"},{"value":"9783030012250","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01225-0_36","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T08:39:54Z","timestamp":1538987994000},"page":"608-624","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":121,"title":["Value-Aware Quantization for Training and Inference of Neural Networks"],"prefix":"10.1007","author":[{"given":"Eunhyeok","family":"Park","sequence":"first","affiliation":[]},{"given":"Sungjoo","family":"Yoo","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Vajda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","first-page":"208","DOI":"10.15803\/ijnc.7.2_208","volume":"7","author":"D Bakunas-Milanowski","year":"2017","unstructured":"Bakunas-Milanowski, D.: Efficient algorithms for stream compaction on GPUs. Int. J. Netw. Comput. (IJNC) 7, 208\u2013226 (2017)","journal-title":"Int. J. Netw. Comput. (IJNC)"},{"key":"36_CR2","unstructured":"Chen, T., et al.: Training deep nets with sublinear memory cost. arXiv:1604.06174 (2016)"},{"key":"36_CR3","unstructured":"De Sa, C., et al.: High-accuracy low-precision training. arXiv:1803.03383 (2018)"},{"key":"36_CR4","unstructured":"Ginsburg, B., et al.: NVIDIA mixed precision training on volta GPUs. In: GPU Technology Conference (2017)"},{"key":"36_CR5","unstructured":"Gomez, A.N., et al.: The reversible residual network: backpropagation without storing activations. In: Advances in Neural Information Processing Systems (NIPS) (2017)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Hazelwood, K., et al.: Applied machine learning at facebook: a datacenter infrastructure perspective. In: International Symposium on High-Performance Computer Architecture (HPCA) (2018)","DOI":"10.1109\/HPCA.2018.00059"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Practical lessons from predicting clicks on ads at facebook. In: International Workshop on Data Mining for Online Advertising (ADKDD) (2014)","DOI":"10.1145\/2648584.2648589"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Hong, S., Kim, H.: An integrated GPU power and performance model. In: International Symposium on Computer Architecture (ISCA) (2010)","DOI":"10.1145\/1815961.1815998"},{"key":"36_CR9","unstructured":"Hubara, I., et al.: Quantized neural networks: training neural networks with low precision weights and activations. arXiv:1609.07061 (2016)"},{"key":"36_CR10","unstructured":"Inan, H., Khosravi, K., Socher, R.: Tying word vectors and word classifiers: a loss framework for language modeling. arXiv:1611.01462 (2016)"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Jain, A., et al.: Gist: efficient data encoding for deep neural network training. In: International Symposium on Computer Architecture (ISCA) (2018)","DOI":"10.1109\/ISCA.2018.00070"},{"key":"36_CR12","unstructured":"Jia, Y., Peter, V.: Delivering real-time AI in the palm of your hand. https:\/\/code.facebook.com\/posts\/196146247499076\/delivering-real-time-ai-in-the-palm-of-your-hand\/. Accessed 25 July 2018"},{"key":"36_CR13","unstructured":"Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: International Symposium on Computer Architecture (ISCA) (2017)"},{"key":"36_CR14","unstructured":"Kone\u010dn\u1ef3, J., et al.: Federated learning: Strategies for improving communication efficiency. arXiv:1610.05492 (2016)"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. arXiv:1805.00932 (2018)","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Marcel, S., Rodriguez, Y.: Torchvision the machine-vision package of torch. In: ACM Multimedia (2010)","DOI":"10.1145\/1873951.1874254"},{"issue":"2","key":"36_CR17","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus, M.P., Marcinkiewicz, M.A., Santorini, B.: Building a large annotated corpus of English: the Penn Treebank. Comput. Linguist. 19(2), 313\u2013330 (1993)","journal-title":"Comput. Linguist."},{"key":"36_CR18","unstructured":"Migacz, S.: NVIDIA 8-bit inference width TensorRT. In: GPU Technology Conference (2017)"},{"key":"36_CR19","unstructured":"Mishra, A., Marr, D.: Apprentice: using knowledge distillation techniques to improve low-precision network accuracy. arXiv:1711.05852 (2017)"},{"key":"36_CR20","unstructured":"Mishra, A., et al.: WRPN: Wide reduced-precision networks. arXiv:1709.01134 (2017)"},{"key":"36_CR21","unstructured":"Miyashita, D., Lee, E.H., Murmann, B.: Convolutional neural networks using logarithmic data representation. arXiv:1603.01025 (2016)"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Park, E., Ahn, J., Yoo, S.: Weighted-entropy-based quantization for deep neural networks. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.761"},{"key":"36_CR23","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":"36_CR24","unstructured":"Paszke, A., et al.: Pytorch (2017)"},{"key":"36_CR25","unstructured":"Polino, A., Pascanu, R., Alistarh, D.: Model compression via distillation and quantization. In: International Conference on Learning Representation (ICLR) (2018)"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Press, O., Wolf, L.: Using the output embedding to improve language models. In: European Chapter of the Association for Computational Linguistics (EACL) (2017)","DOI":"10.18653\/v1\/E17-2025"},{"key":"36_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":"36_CR28","doi-asserted-by":"crossref","unstructured":"Umuroglu, Y., et al.: Finn: A framework for fast, scalable binarized neural network inference. Architecture of Field-Programmable Gate Arrays (FPGA) (2017)","DOI":"10.1145\/3020078.3021744"},{"key":"36_CR29","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv:1409.2329 (2014)"},{"key":"36_CR30","unstructured":"Zhou, S., et al.: Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv:1606.06160 (2016)"},{"issue":"4","key":"36_CR31","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1007\/s11390-017-1750-y","volume":"32","author":"S Zhou","year":"2017","unstructured":"Zhou, S.: Balanced quantization: an effective and efficient approach to quantized neural networks. J. Comput. Sci. Technol. 32(4), 667\u2013682 (2017)","journal-title":"J. Comput. Sci. Technol."},{"key":"36_CR32","unstructured":"Zhu, C., et al.: Trained ternary quantization. arXiv:1612.01064 (2016)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01225-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:12:19Z","timestamp":1665187939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01225-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012243","9783030012250"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01225-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}