{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:54:19Z","timestamp":1776783259052,"version":"3.51.2"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030419639","type":"print"},{"value":"9783030419646","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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-41964-6_40","type":"book-chapter","created":{"date-parts":[[2020,3,3]],"date-time":"2020-03-03T12:03:51Z","timestamp":1583237031000},"page":"467-479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Post-training Quantization Methods for Deep Learning Models"],"prefix":"10.1007","author":[{"given":"Piotr","family":"Kluska","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maciej","family":"Zi\u0119ba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,4]]},"reference":[{"key":"40_CR1","unstructured":"Andrew, H., et al.: Searching for MobileNetV3, Technical report (2019). \nhttp:\/\/arxiv.org\/abs\/1905.02244"},{"key":"40_CR2","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D.: Post training 4-bit quantization of convolution networks for rapid-deployment. Technical report (2018). \nhttps:\/\/arxiv.org\/pdf\/1810.05723.pdf"},{"key":"40_CR3","unstructured":"Benoit, J., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. Technical report (2017). \nhttps:\/\/arxiv.org\/pdf\/1712.05877.pdf"},{"key":"40_CR4","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.J., Srinivasan, V., Gopalakrishnan, K.: PACT: parameterized clipping activation for quantized neural networks. Technical report (2018). \nhttp:\/\/arxiv.org\/abs\/1805.06085"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Dally, W.J., et al.: Hardware-enabled artificial intelligence. \nhttps:\/\/research.nvidia.com\/sites\/default\/files\/pubs\/2018-06_Hardware-Enabled-Artificial-Intelligence\/VLSI2018_HardwareAI.pdf.PDF","DOI":"10.1109\/VLSIC.2018.8502368"},{"issue":"2","key":"40_CR6","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"40_CR7","doi-asserted-by":"publisher","first-page":"5784","DOI":"10.1109\/TNNLS.2018.2808319","volume":"29","author":"P Gysel","year":"2018","unstructured":"Gysel, P., Pimentel, J., Motamedi, M., Ghiasi, S.: Ristretto: a framework for empirical study of resource-efficient inference in convolutional neural networks. IEEE Trans. Neural Netw. Learn. Syst. 29(11), 5784\u20135789 (2018). \nhttps:\/\/doi.org\/10.1109\/TNNLS.2018.2808319","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"40_CR8","unstructured":"Hacene, G.B., Gripon, V., Arzel, M., Farrugia, N., Bengio, Y.: Quantized guided pruning for efficient hardware implementations of convolutional neural networks. Technical report (2018). \nhttps:\/\/arxiv.org\/pdf\/1812.11337.pdf"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Han, S., Dally, W.J.: Bandwidth-efficient deep learning. In: 2018 55th ACM\/ESDA\/IEEE Design Automation Conference (DAC), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/DAC.2018.8465812"},{"key":"40_CR10","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Technical report (2016). \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.90\n\n. \nhttp:\/\/image-net.org\/challenges\/LSVRC\/2015\/","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR11","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: alexnet-level accuracy with 50x fewer parameters and $$<$$0.5MB model size. Technical report (2016). \nhttp:\/\/arxiv.org\/abs\/1602.07360"},{"key":"40_CR12","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference Computer Vision Pattern Recognition, pp. 248\u2013255 (2009). \nhttps:\/\/doi.org\/10.1109\/CVPRW.2009.5206848\n\n. \nhttp:\/\/ieeexplore.ieee.org\/lpdocs\/epic03\/wrapper.htm?arnumber=5206848","DOI":"10.1109\/CVPRW.2009.5206848"},{"key":"40_CR13","unstructured":"Krishnamoorthi, R.: Quantizing deep convolutional networks for efficient inference: a whitepaper. arXiv preprint \narXiv:1806.08342\n\n (2018)"},{"key":"40_CR14","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Technical report (2012)"},{"key":"40_CR15","unstructured":"Li, F., Zhang, B., Liu, B.: Ternary weight networks (2016). \nhttps:\/\/github.com\/fengfu-chris\/caffe-twns\n\n. \nhttp:\/\/arxiv.org\/abs\/1605.04711"},{"key":"40_CR16","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient ConvNets. Technical report (2016). \nhttp:\/\/arxiv.org\/abs\/1608.08710"},{"key":"40_CR17","unstructured":"Lin, D.D., Talathi, S.S., Annapureddy, V.S.: Fixed point quantization of deep convolutional networks. Technical reports (2016). \nhttps:\/\/arxiv.org\/pdf\/1511.06393.pdf"},{"key":"40_CR18","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3686\u20133693 (2015). \nhttps:\/\/doi.org\/10.1109\/CVPR.2014.471\n\n. \nhttp:\/\/arxiv.org\/abs\/1405.0312","DOI":"10.1109\/CVPR.2014.471"},{"key":"40_CR19","unstructured":"Migacz, S.: 8-bit inference with TensorRT. In: GPU Technology Conference (2017). \nhttp:\/\/on-demand.gputechconf.com\/gtc\/2017\/presentation\/s7310-8-bit-inference-with-tensorrt.pdf"},{"key":"40_CR20","doi-asserted-by":"publisher","unstructured":"Nakahara, H., Yonekawa, H., Fujii, T., Sato, S.: A lightweight yolov2: a binarized CNN with a parallel support vector regression for an FPGA, pp. 31\u201340 (2018). \nhttps:\/\/doi.org\/10.1145\/3174243.3174266","DOI":"10.1145\/3174243.3174266"},{"key":"40_CR21","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). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46493-0_32"},{"key":"40_CR22","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of 30th IEEE Conference on Computer Vision on Pattern Recognition, CVPR 2017, pp. 6517\u20136525 (2017). \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.690\n\n. \nhttp:\/\/pjreddie.com\/yolo9000\/","DOI":"10.1109\/CVPR.2017.690"},{"key":"40_CR23","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. Technical report (2018). \nhttp:\/\/arxiv.org\/abs\/1804.02767"},{"issue":"6","key":"40_CR24","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). \nhttps:\/\/doi.org\/10.1109\/TPAMI.2016.2577031\n\n. \nhttp:\/\/image-net.org\/challenges\/LSVRC\/2015\/results\n\n. \nhttp:\/\/www.ncbi.nlm.nih.gov\/pubmed\/27295650","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR25","doi-asserted-by":"publisher","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018). \nhttps:\/\/doi.org\/10.1109\/CVPR.2018.00474\n\n. \nhttps:\/\/arxiv.org\/pdf\/1801.04381.pdf","DOI":"10.1109\/CVPR.2018.00474"},{"key":"40_CR26","unstructured":"Sultana, F., Sufian, A., Dutta, P.: A review of object detection models based on convolutional neural network. Technical report (2019). \nhttp:\/\/arxiv.org\/abs\/1905.01614"},{"key":"40_CR27","unstructured":"Sung, W., Shin, S., Hwang, K.: Resiliency of deep neural networks under quantization (2015). \nhttps:\/\/arxiv.org\/pdf\/1511.06488.pdf"},{"key":"40_CR28","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. Technical report (2016). \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.308\n\n. \nhttps:\/\/arxiv.org\/pdf\/1512.00567.pdf","DOI":"10.1109\/CVPR.2016.308"},{"key":"40_CR29","unstructured":"Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile (2018). \nhttps:\/\/github.com\/tensorflow\/tpu\/\n\n. \nhttp:\/\/arxiv.org\/abs\/1807.11626"},{"key":"40_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8612\u20138620 (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"40_CR31","unstructured":"Wei, Y., Pan, X., Qin, H., Ouyang, W., Yan, J.: Quantization mimic: towards very tiny CNN for object detection. Technical report. \nhttps:\/\/arxiv.org\/pdf\/1805.02152v3.pdf"},{"key":"40_CR32","unstructured":"Ye, S., et al.: Progressive DNN compression: a key to achieve ultra-high weight pruning and quantization rates using ADMM (2019). \nhttps:\/\/bit.ly\/2TYx7Za\n\n. \nhttp:\/\/arxiv.org\/abs\/1903.09769"},{"key":"40_CR33","unstructured":"Yin, P., Zhang, S., Qi, Y., Xin, J.: Quantization and training of low bit-width convolutional neural networks for object detection (2016). \nhttps:\/\/arxiv.org\/pdf\/1612.06052v2.pdf\n\n. \nhttp:\/\/arxiv.org\/abs\/1612.06052"},{"key":"40_CR34","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 (2016). \nhttp:\/\/arxiv.org\/abs\/1606.06160"}],"container-title":["Lecture Notes in Computer Science","Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41964-6_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T00:32:38Z","timestamp":1584059558000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41964-6_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030419639","9783030419646"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41964-6_40","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":"4 March 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Phuket","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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 March 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 March 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}