{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:50:07Z","timestamp":1778082607178,"version":"3.51.4"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0103402"],"award-info":[{"award-number":["2020AAA0103402"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906193"],"award-info":[{"award-number":["61906193"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDA27040300"],"award-info":[{"award-number":["XDA27040300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,2,1]]},"DOI":"10.1109\/tpami.2022.3159369","type":"journal-article","created":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T19:47:33Z","timestamp":1647373653000},"page":"2119-2135","source":"Crossref","is-referenced-by-count":34,"title":["Optimization-Based Post-Training Quantization With Bit-Split and Stitching"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6384-0280","authenticated-orcid":false,"given":"Peisong","family":"Wang","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihan","family":"Chen","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"He","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4373-2589","authenticated-orcid":false,"given":"Qiang","family":"Chen","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5512-6984","authenticated-orcid":false,"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[{"name":"B-DAT, Nanjing University of Information Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1289-2758","authenticated-orcid":false,"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref6","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3020257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700789"},{"key":"ref11","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967280"},{"key":"ref14","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Romero"},{"key":"ref15","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"2018"},{"key":"ref16","article-title":"8-bit inference with TensorRT","volume-title":"Proc. GPU Technol. Conf.","author":"Migacz"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"ref19","first-page":"7948","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Banner"},{"key":"ref20","first-page":"243","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref22","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref23","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014"},{"key":"ref24","first-page":"1","article-title":"And the bit goes down: Revisiting the quantization of neural networks","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Stock"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"key":"ref26","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref27","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref28","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Courbariaux"},{"key":"ref29","first-page":"4114","article-title":"Binarized neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6900"},{"key":"ref34","first-page":"1","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00460"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00452"},{"key":"ref37","first-page":"1","article-title":"Learned step size quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Esser"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref40","first-page":"1","article-title":"Low precision arithmetic for deep learning","volume-title":"Proc. 3rd Int. Conf. Learn. Representations Workshop","author":"Courbariaux"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062259"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240803"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.422"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_39"},{"key":"ref45","first-page":"344","article-title":"Towards accurate binary convolutional neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00506"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.282"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10862"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_37"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01540"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06053-z"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_5"},{"key":"ref55","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref56","volume-title":"Second Order Derivatives for Network Pruning: Optimal Brain Surgeon","author":"Hassibi","year":"1993"},{"key":"ref57","first-page":"5113","article-title":"Collaborative channel pruning for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref59","first-page":"1","article-title":"Trace weighted hessian-aware quantization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshops","author":"Dong"},{"key":"ref60","first-page":"18 518","article-title":"HAWQ-V2: Hessian aware trace-weighted quantization of neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref61","first-page":"1","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lebedev"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11660"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref64","first-page":"4857","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref65","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nagel"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714901"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00301"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116359"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2019.2949935"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"ref71","first-page":"1","article-title":"High performance convolutional neural networks for document processing","volume-title":"Proc. 10th Int. Workshop Front. Handwriting Recognit.","author":"Chellapilla"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00852"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10008914\/09735379.pdf?arnumber=9735379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:17:38Z","timestamp":1705533458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9735379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":76,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3159369","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,1]]}}}