{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T12:10:45Z","timestamp":1753359045444,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031197741"},{"type":"electronic","value":"9783031197758"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19775-8_10","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"157-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["RDO-Q: Extremely Fine-Grained Channel-Wise Quantization via\u00a0Rate-Distortion Optimization"],"prefix":"10.1007","author":[{"given":"Zhe","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jie","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Xue","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Mohamed M. Sabry","family":"Aly","sequence":"additional","affiliation":[]},{"given":"Vijay","family":"Chandrasekhar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"10_CR1","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D.: Post-training 4-bit quantization of convolution networks for rapid-deployment. arXiv preprint. arXiv:1810.05723 (2018)"},{"key":"10_CR2","unstructured":"Bengio, Y., Leonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. In: arXiv:1308.3432 (2013)"},{"issue":"1","key":"10_CR3","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","volume":"52","author":"YH Chen","year":"2016","unstructured":"Chen, Y.H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circ. 52(1), 127\u2013138 (2016)","journal-title":"IEEE J. Solid-State Circ."},{"key":"10_CR4","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.J., Srinivasan, V., Gopalakrishnan, K.: Pact: parameterized clipping activation for quantized neural networks. In: arXiv (2018)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Dong, Z., Yao, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: Hawq: Hessian aware quantization of neural networks with mixed-precision. In: arXiv (2019)","DOI":"10.1109\/ICCV.2019.00038"},{"key":"10_CR7","unstructured":"Elthakeb, A.T., Pilligundla, P., Mireshghallah, F., Yazdanbakhsh, A., Esmaeilzadeh, H.: Releq: a reinforcement learning approach for deep quantization of neural networks. In: NeurIPS Workshop on ML for Systems (2018)"},{"key":"10_CR8","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.: Learned step size quantization. In: ICLR (2020)"},{"key":"10_CR9","unstructured":"Gao, W., Liu, Y.H., Wang, C., Oh, S.: Rate distortion for model compression: from theory to practice. In: International Conference on Machine Learning, pp. 2102\u20132111. PMLR (2019)"},{"key":"10_CR10","volume-title":"Vector Quantization and Signal Compression","author":"A Gersho","year":"1991","unstructured":"Gersho, A., Gray, R.: Vector Quantization and Signal Compression. Kluwer Academic Publishers, Dordrecht (1991)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Gong, R., et al.: Differentiable soft quantization: Bridging full-precision and low-bit neural networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00495"},{"key":"10_CR12","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. In: ICLR (2016)"},{"key":"10_CR13","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. arXiv preprint. arXiv:1506.02626 (2015)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR15","unstructured":"Jin, Q., Yang, L., Liao, Z., Qian, X.: Neural network quantization with scale-adjusted training. BMVC (2020)"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Jouppi, N., 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. ISCA\u201917, ACM, New York, NY, USA (2017). https:\/\/doi.org\/10.1145\/3079856.3080246, http:\/\/doi.acm.org\/10.1145\/3079856.3080246","DOI":"10.1145\/3079856.3080246"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Jung, S., et al.: Learning to quantize deep networks by optimizing quantization intervals with task loss. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00448"},{"key":"10_CR18","unstructured":"Khoram, S., Li, J.: Adaptive quantization of neural networks. In: ICLR (2018)"},{"key":"10_CR19","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"issue":"7553","key":"10_CR20","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"10_CR21","unstructured":"Li, Y., Dong, X., Wang, W.: Additive powers-of-two quantization: an efficient non-uniform discretization for neural networks. In: ICLR (2020)"},{"key":"10_CR22","unstructured":"Lou, Q., Guo, F., Kim, M., Liu, L., Jiang, L.: Autoq: automated kernel-wise neural network quantizations. In: ICLR (2020)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Qu, Z., Zhou, Z., Cheng, Y., Thiele, L.: Adaptive loss-aware quantization for multi-bit networks. In: arXiv (2020)","DOI":"10.1109\/CVPR42600.2020.00801"},{"key":"10_CR24","unstructured":"Samajdar, A., Zhu, Y., Whatmough, P.N., Mattina, M., Krishna, T.: Scale-sim: systolic CNN accelerator. CoRR abs\/1811.02883, http:\/\/arxiv.org\/abs\/1811.02883 (2018)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: arXiv (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Shoham, Y., Gersho, A.: Efficient bit allocation for an arbitrary set of quantizers (speech coding. In: IEEE Transactions on Acoustics, Speech, and Signal Processing (1988)","DOI":"10.1109\/29.90373"},{"key":"10_CR27","volume-title":"Reinforcement Learning: An introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An introduction. MIT press, Cambridge (2018)"},{"key":"10_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0799-4","volume-title":"JPEG 2000 Image Compression Fundamentals, Standards and Practice","author":"DS Taubman","year":"2002","unstructured":"Taubman, D.S., Marcellin, M.W.: JPEG 2000 Image Compression Fundamentals, Standards and Practice. Springer, New York (2002). https:\/\/doi.org\/10.1007\/978-1-4615-0799-4"},{"key":"10_CR29","unstructured":"Uhlich, S., et al.: Mixed precision dnns: all you need is a good parametrization. arXiv preprint. arXiv:1905.11452 (2019)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: Haq: hardware-aware automated quantization with mixed precision. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"10_CR31","unstructured":"Wu, B., Wang, Y., Zhang, P., Tian, Y., Vajda, P., Keutzer, K.: Mixed precision quantization of convnets via differentiable neural architecture search. In: ICLR (2019)"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Yang, L., Jin, Q.: Fracbits: mixed precision quantization via fractional bit-widths. arXiv preprint. arXiv:2007.02017 (2020)","DOI":"10.1609\/aaai.v35i12.17269"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yang, J., Ye, D., Hua, G.: Lq-nets: learned quantization for highly accurate and compact deep neural networks. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, S., Yue, T., Hu, X.: Distribution-aware adaptive multi-bit quantization. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00916"},{"key":"10_CR35","unstructured":"Zhao, X., Wang, Y., Cai, X., Liu, C., Zhang, L.: Linear symmetric quantization of neural networks for low-precision integer hardware. ICLR (2020)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Zhe, W., Lin, J., Aly, M.S., Young, S., Chandrasekhar, V., Girod, B.: Rate-distortion optimized coding for efficient cnn compression. In: DCC (2021)","DOI":"10.1109\/DCC50243.2021.00033"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Zhe, W., Lin, J., Chandrasekhar, V., Girod, B.: Optimizing the bit allocation for compression of weights and activations of deep neural networks. In: ICIP (2019)","DOI":"10.1109\/ICIP.2019.8803498"},{"key":"10_CR38","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: Dorefa-net: training low bitwidth convolutional neural networks with low bitwidth gradients. In: arXiv preprint. arXiv:1606.06160 (2016)"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Moosavi-Dezfooli, S.M., Cheung, N.M., Frossard, P.: Adaptive quantization for deep neural network. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11623"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Liu, L., Tan, M., Shen, C., Reid, I.: Training quantized neural networks with a full-precision auxiliary module. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00156"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Shen, C., Tan, M., Liu, L., Reid, I.: Towards effective low-bitwidth convolutional neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00826"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19775-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:37:02Z","timestamp":1710337022000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19775-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197741","9783031197758"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19775-8_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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)"}}]}}