{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T06:44:00Z","timestamp":1743576240618,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031250811"},{"type":"electronic","value":"9783031250828"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25082-8_5","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T09:12:42Z","timestamp":1676106762000},"page":"67-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Power Awareness in\u00a0Low Precision Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5277-3182","authenticated-orcid":false,"given":"Nurit Spingarn","family":"Eliezer","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-7830","authenticated-orcid":false,"given":"Ron","family":"Banner","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8932-2126","authenticated-orcid":false,"given":"Hilla","family":"Ben-Yaakov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7339-1431","authenticated-orcid":false,"given":"Elad","family":"Hoffer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0525-8054","authenticated-orcid":false,"given":"Tomer","family":"Michaeli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Abts, D., et al.: Think fast: a tensor streaming processor (tsp) for accelerating deep learning workloads. In: 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), pp. 145\u2013158. IEEE (2020)","DOI":"10.1109\/ISCA45697.2020.00023"},{"key":"5_CR2","unstructured":"Achterhold, J., Koehler, J.M., Schmeink, A., Genewein, T.: Variational network quantization. In: International Conference on Learning Representations (2018)"},{"key":"5_CR3","unstructured":"Asif, S., Kong, Y.: Performance analysis of wallace and radix-4 booth-wallace multipliers. In: 2015 Electronic System Level Synthesis Conference (ESLsyn), pp. 17\u201322. IEEE (2015)"},{"key":"5_CR4","unstructured":"Banner, R., Nahshan, Y., Soudry, D.: Post training 4-bit quantization of convolutional networks for rapid-deployment. In: Advances in Neural Information Processing Systems, pp. 7950\u20137958 (2019)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Y., Yao, Z., Dong, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: Zeroq: a novel zero shot quantization framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13169\u201313178 (2020)","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Addernet: do we really need multiplications in deep learning? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1468\u20131477 (2020)","DOI":"10.1109\/CVPR42600.2020.00154"},{"key":"5_CR7","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: Binaryconnect: training deep neural networks with binary weights during propagations. arXiv preprint arXiv:1511.00363 (2015)"},{"key":"5_CR8","unstructured":"Elhoushi, M., Chen, Z., Shafiq, F., Tian, Y.H., Li, J.Y.: Deepshift: towards multiplication-less neural networks. arXiv preprint arXiv:1905.13298 (2019)"},{"key":"5_CR9","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned step size quantization. In: International Conference on Learning Representations (2019)"},{"key":"5_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-030-58536-5_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Fang","year":"2020","unstructured":"Fang, J., Shafiee, A., Abdel-Aziz, H., Thorsley, D., Georgiadis, G., Hassoun, J.H.: Post-training piecewise linear quantization for deep neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 69\u201386. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_5"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Gudaparthi, S., Narayanan, S., Balasubramonian, R., Giacomin, E., Kambalasubramanyam, H., Gaillardon, P.E.: Wire-aware architecture and dataflow for CNN accelerators. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 1\u201313 (2019)","DOI":"10.1145\/3352460.3358316"},{"key":"5_CR12","unstructured":"Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: International Conference on Machine Learning, pp. 1737\u20131746 (2015)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Haroush, M., Hubara, I., Hoffer, E., Soudry, D.: The knowledge within: Methods for data-free model compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8494\u20138502 (2020)","DOI":"10.1109\/CVPR42600.2020.00852"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Horowitz, M.: Computing\u2019s energy problem (and what we can do about it). In:2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pp. 10\u201314 (2014)","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"5_CR15","unstructured":"Horowitz, M.: Energy table for 45nm process. In: Stanford VLSI wiki (2014)"},{"key":"5_CR16","unstructured":"Huang, N.C., Chou, H.J., Wu, K.C.: Efficient systolic array based on decomposable mac for quantized deep neural networks (2019)"},{"key":"5_CR17","unstructured":"Hubara, I., Nahshan, Y., Hanani, Y., Banner, R., Soudry, D.: Improving post training neural quantization: Layer-wise calibration and integer programming. arXiv preprint arXiv:2006.10518 (2020)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Jiao, Y., et al.: 7.2 a 12nm programmable convolution-efficient neural-processing-unit chip achieving 825tops. In: 2020 IEEE International Solid-State Circuits Conference-(ISSCC), pp. 136\u2013140. IEEE (2020)","DOI":"10.1109\/ISSCC19947.2020.9062984"},{"key":"5_CR20","unstructured":"Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)"},{"key":"5_CR21","unstructured":"Kalamkar, D.,et al.: A study of bfloat16 for deep learning training. arXiv preprint arXiv:1905.12322 (2019)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Karimi, N., Moos, T., Moradi, A.: Exploring the effect of device aging on static power analysis attacks. UMBC Faculty Collection (2019)","DOI":"10.46586\/tches.v2019.i3.233-256"},{"key":"5_CR23","unstructured":"Kim, Y., Park, E., Yoo, S., Choi, T., Yang, L., Shin, D.: Compression of deep convolutional neural networks for fast and low power mobile applications. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2\u20134, 2016, Conference Track Proceedings (2016). http:\/\/arxiv.org\/abs\/1511.06530"},{"issue":"3","key":"5_CR24","doi-asserted-by":"publisher","first-page":"478","DOI":"10.3390\/electronics9030478","volume":"9","author":"Y Kim","year":"2020","unstructured":"Kim, Y., Kim, H., Yadav, N., Li, S., Choi, K.K.: Low-power RTL code generation for advanced CNN algorithms toward object detection in autonomous vehicles. Electronics 9(3), 478 (2020)","journal-title":"Electronics"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Kwon, H., Chatarasi, P., Pellauer, M., Parashar, A., Sarkar, V., Krishna, T.: Understanding reuse, performance, and hardware cost of DNN dataflow: a data-centric approach. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 754\u2013768 (2019)","DOI":"10.1145\/3352460.3358252"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4013\u20134021 (2016)","DOI":"10.1109\/CVPR.2016.435"},{"key":"5_CR27","unstructured":"Li, F., Zhang, B., Liu, B.: Ternary weight networks. arXiv preprint arXiv:1605.04711 (2016)"},{"key":"5_CR28","unstructured":"Li, Y., et al.: BRECQ: pushing the limit of post-training quantization by block reconstruction. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=POWv6hDd9XH"},{"key":"5_CR29","unstructured":"Lin, Z., Courbariaux, M., Memisevic, R., Bengio, Y.: Neural networks with few multiplications. arXiv preprint arXiv:1510.03009 (2015)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Liu, X., Ye, M., Zhou, D., Liu, Q.: Post-training quantization with multiple points: Mixed precision without mixed precision. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 8697\u20138705 (2021)","DOI":"10.1609\/aaai.v35i10.17054"},{"key":"5_CR31","unstructured":"Louizos, C., Reisser, M., Blankevoort, T., Gavves, E., Welling, M.: Relaxed quantization for discretized neural networks. arXiv preprint arXiv:1810.01875 (2018)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Mahmoud, M.: Tensordash: Exploiting sparsity to accelerate deep neural network training and inference (2020)","DOI":"10.1109\/MICRO50266.2020.00069"},{"key":"5_CR33","unstructured":"Mishra, A., Nurvitadhi, E., Cook, J.J., Marr, D.: WRPN: wide reduced-precision networks. arXiv preprint arXiv:1709.01134 (2017)"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Mukherjee, A., Saurav, K., Nair, P., Shekhar, S., Lis, M.: A case for emerging memories in dnn accelerators. In: 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 938\u2013941. IEEE (2021)","DOI":"10.23919\/DATE51398.2021.9474252"},{"key":"5_CR35","unstructured":"Nagel, M., Amjad, R.A., van Baalen, M., Louizos, C., Blankevoort, T.: Up or down? adaptive rounding for post-training quantization. arXiv preprint arXiv:2004.10568 (2020)"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Nagel, M., Baalen, M.v., Blankevoort, T., Welling, M.: Data-free quantization through weight equalization and bias correction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1325\u20131334 (2019)","DOI":"10.1109\/ICCV.2019.00141"},{"key":"5_CR37","unstructured":"Nahshan, Y., et al.: Loss aware post-training quantization. arXiv preprint arXiv:1911.07190 (2019)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Nasser, Y., Pr\u00e9votet, J.C., H\u00e9lard, M., Lorandel, J.: Dynamic power estimation based on switching activity propagation. In: 2017 27th International Conference on Field Programmable Logic and Applications (FPL), pp. 1\u20132. IEEE (2017)","DOI":"10.23919\/FPL.2017.8056783"},{"key":"5_CR39","unstructured":"Ni, R., Chu, H.m., Castaneda Fernandez, O., Chiang, P.V., Studer, C., Goldstein, T.: Wrapnet: Neural net inference with ultra-low-precision arithmetic. In: 9th International Conference on Learning Representations (ICLR 2021) (2021)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"5_CR41","first-page":"1","volume":"3","author":"A Rodriguez","year":"2018","unstructured":"Rodriguez, A., et al.: Lower numerical precision deep learning inference and training. Intel White Paper 3, 1\u201319 (2018)","journal-title":"Intel White Paper"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"5_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58610-2_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Xu","year":"2020","unstructured":"Xu, S., et al.: Generative low-bitwidth data free quantization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 1\u201317. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_1"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Tam, E., et al.: Breaking the memory wall for AI chip with a new dimension. In: 2020 5th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM), pp. 1\u20137. IEEE (2020)","DOI":"10.1109\/SEEDA-CECNSM49515.2020.9221795"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Tan, M., et al.: Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2820\u20132828 (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"5_CR46","unstructured":"Tschannen, M., Khanna, A., Anandkumar, A.: StrassenNets: deep learning with a multiplication budget. In: International Conference on Machine Learning. pp. 4985\u20134994. PMLR (2018)"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Venkatesh, G., Nurvitadhi, E., Marr, D.: Accelerating deep convolutional networks using low-precision and sparsity (2016)","DOI":"10.1109\/ICASSP.2017.7952679"},{"key":"5_CR48","unstructured":"You, H., et al.: ShiftaddNet: a hardware-inspired deep network. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25082-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T13:02:08Z","timestamp":1709816528000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25082-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250811","9783031250828"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25082-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"12 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}