{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:26:14Z","timestamp":1781537174016,"version":"3.54.5"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tetci.2024.3510295","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:47:32Z","timestamp":1734551252000},"page":"2597-2617","source":"Crossref","is-referenced-by-count":7,"title":["Low-Bit Mixed-Precision Quantization and Acceleration of CNN for FPGA Deployment"],"prefix":"10.1109","volume":"9","author":[{"given":"JianRong","family":"Wang","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-4894","authenticated-orcid":false,"given":"Zhijun","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Telecommunication and Navigation Satellites, China Academy of Space Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1196-4089","authenticated-orcid":false,"given":"Hongbo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3098-8649","authenticated-orcid":false,"given":"Rongke","family":"Liu","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2020.02.44"},{"key":"ref2","first-page":"980","article-title":"Global filter networks for image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2014.2307227"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/23270012.2020.1756939"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC51019.2021.9418274"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545450"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01468"},{"key":"ref12","first-page":"3105","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Bengio","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808319"},{"key":"ref14","article-title":"Wrapnet: Neural net inference with ultra-low-resolution arithmetic","author":"Renkun","year":"2020"},{"key":"ref15","article-title":"Xnor-net: Improved binary neural networks","author":"Bulat","year":"2019"},{"key":"ref16","article-title":"Pact: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018"},{"key":"ref17","article-title":"Training with quantization noise for extreme model compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Stock","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00826"},{"key":"ref19","article-title":"Degree-quant: Quantization-aware training for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tailor","year":"2020"},{"key":"ref20","first-page":"7950","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Banner","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"ref22","first-page":"69","article-title":"Post-training piecewise linear quantization for deep neural networks","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Jun","year":"2020"},{"key":"ref23","article-title":"Confounding tradeoffs for neural network quantization","author":"Garg","year":"2021"},{"key":"ref24","first-page":"752","article-title":"Learning compression from limited unlabeled data","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Xiangyu","year":"2018"},{"key":"ref25","first-page":"17737","article-title":"Post-training sparsity-aware quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Shomron","year":"2021"},{"key":"ref26","first-page":"7543","article-title":"Improving neural network quantization without retraining using outlier channel splitting","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Zhao","year":"2019"},{"key":"ref27","article-title":"Improving post training neural quantization: Layer-wise calibration and integer programming","author":"Hubara","year":"2020"},{"key":"ref28","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"ref30","first-page":"45","article-title":"Optimizing loop operation and dataflow in FPGA acceleration of deep convolutional neural networks","volume-title":"Proc. ACMSIGDA Int. Symp. Field-Programmable Gate Arrays","author":"Yufei","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.64"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2016.7428073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577308"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2016.7929190"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240801"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2705069"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1145\/1854273.1854309","article-title":"A programmable parallel accelerator for learning and classification","volume-title":"Proc. 19th Int. Conf. Parallel Architectures Compilation Techn.","author":"Cadambi","year":"2010"},{"key":"ref41","article-title":"EasyQuant: Post-training quantization via scale optimization","author":"Di","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3078541"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474597"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00013"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3048624"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080221"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3079758"},{"key":"ref48","article-title":"EdgeQAT: Entropy and distribution guided quantization-aware training for the acceleration of lightweight LLMs on the edge","author":"Shen","year":"2024"},{"key":"ref49","article-title":"KV cache is 1 bit per channel: Efficient large language model inference with coupled quantization","author":"Zhang","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00530"},{"key":"ref51","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Lin","year":"2024"},{"key":"ref52","article-title":"QDrop: Randomly dropping quantization for extremely low-bit post-training quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01509"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00144"},{"key":"ref55","first-page":"7197","article-title":"Up or down Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nagel","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00801"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00386"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_10"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_1"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00054"},{"key":"ref61","first-page":"873","article-title":"Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Dai","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3315299"},{"key":"ref63","article-title":"SQuant: On-the-fly data-free quantization via diagonal Hessian approximation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guo","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3084839"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3198246"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/FPL53798.2021.00011"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/11016134\/10806654.pdf?arnumber=10806654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:42:47Z","timestamp":1748407367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":66,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3510295","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}