{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:34:59Z","timestamp":1784133299618,"version":"3.55.0"},"reference-count":174,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650109","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-10","source":"Crossref","is-referenced-by-count":30,"title":["Contemporary Advances in Neural Network Quantization: A Survey"],"prefix":"10.1109","author":[{"given":"Min","family":"Li","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Huang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxing","family":"Ren","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengfa","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jitao","family":"Fu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenghua","family":"Gao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref5","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref8","article-title":"Predicting parameters in deep learning","volume":"26","author":"Denil","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume":"30","author":"Dong","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume":"5","author":"Hassibi","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Optimal brain damage","volume":"2","author":"LeCun","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Snip: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6910"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2008.45"},{"key":"ref18","article-title":"The state of sparsity in deep neural networks","author":"Gale","year":"2019"},{"key":"ref19","article-title":"Pruning filters for efficient convnets","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref21","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref22","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref25","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref27","article-title":"Model compression via distillation and quantization","author":"Polino","year":"2018"},{"key":"ref28","article-title":"Mobilenets: Efficient convo-lutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref30","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and\u00a1 0.5 mb model size","author":"Iandola","year":"2016"},{"key":"ref31","first-page":"4510","article-title":"Mo-bilenetv2: Inverted residuals and linear bottlenecks","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Sandler"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref33","first-page":"6848","article-title":"Shufflenet: An extremely effi-cient convolutional neural network for mobile devices","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref35","article-title":"Taking human out of learning applications: A survey on automated machine learning","author":"Yao","year":"2018"},{"key":"ref36","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref38","first-page":"1314","article-title":"Searching for mo-bilenetv3","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Howard"},{"key":"ref39","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for con-volutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref40","first-page":"10 096","article-title":"Efficientnetv2: Smaller models and faster training","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref42","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"2018","journal-title":"CoRR"},{"key":"ref43","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"CoRR"},{"key":"ref44","article-title":"Scalable methods for 8-bit training of neural networks","volume":"31","author":"Banner","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref45","article-title":"Neural gradients are near-lognormal: improved quantized and sparse training","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Chmiel"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00067"},{"key":"ref47","first-page":"28 092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00374"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00054"},{"key":"ref50","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"International conference on machine learning","author":"Gupta"},{"key":"ref51","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014"},{"key":"ref52","first-page":"4820","article-title":"Quantized convo-lutional neural networks for mobile devices","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Wu"},{"issue":"1","key":"ref53","first-page":"1","article-title":"Uniq: Uniform noise injection for non-uniform quantization of neural networks","volume":"37","author":"Baskin","year":"2021","journal-title":"ACM Transactions on Computer Systems (TOCS)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref55","article-title":"Convolutional neural networks using logarithmic data representation","author":"Miyashita","year":"2016"},{"key":"ref56","article-title":"Incremental network quantization: Towards lossless cnns with low-precision weights","author":"Zhou","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10862"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.430"},{"key":"ref59","article-title":"Alternating multi-bit quantization for recurrent neural networks","author":"Xu","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref61","article-title":"Towards accurate binary convolutional neural network","volume":"30","author":"Lin","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00748"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774615"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01210"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref68","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2016"},{"key":"ref69","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","volume":"30","author":"Agustsson","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_30"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00351"},{"key":"ref72","article-title":"Incremental few-shot learning via vector quantization in deep embedded space","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00066"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088904"},{"key":"ref76","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume":"32","author":"Banner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref78","first-page":"7543","article-title":"Improving neural network quantization without retraining using outlier channel splitting","volume-title":"International conference on machine learning","author":"Zhao"},{"key":"ref79","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quan-tization","volume-title":"International Conference on Machine Learning","author":"Nagel"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref81","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref82","article-title":"Proxquant: Quantized neural networks via proximal operators","author":"Bai","year":"2018"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2996936"},{"key":"ref84","article-title":"Loss-aware binarization of deep networks","author":"Hou","year":"2016"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"ref86","article-title":"On periodic functions as regularizers for quantization of neural networks","author":"Naumov","year":"2018"},{"key":"ref87","first-page":"4466","article-title":"Accurate post training quantization with small calibration sets","volume-title":"International Conference on Machine Learning","author":"Hubara"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_46"},{"key":"ref89","article-title":"Fighting quantization bias with bias","author":"Finkelstein","year":"2019"},{"key":"ref90","first-page":"4486","article-title":"Same, same but different: Recovering neural network quantization error through weight factorization","volume-title":"International Conference on Machine Learning","author":"Meller"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref92","article-title":"Improving post training neural quantization: Layer-wise calibration and integer programming","author":"Hubara","year":"2020"},{"key":"ref93","article-title":"SQuant: On-the-fly data-free quantization via diagonal hessian approximation","volume-title":"International Conference on Learning Representations","author":"Guo"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00852"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01540"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00437"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00335"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_1"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00363"},{"key":"ref101","first-page":"289","article-title":"Dfqf: Data free quantization-aware fine-tuning","volume-title":"Asian Conference on Machine Learning","author":"Li"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00156"},{"key":"ref103","first-page":"14 835","article-title":"Qimera: Data-free quantization with synthetic boundary supporting samples","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01202"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00024"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00813"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01599"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00769"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26136"},{"key":"ref111","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume":"28","author":"Courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref112","article-title":"Bi-narized neural networks","volume":"29","author":"Hubara","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref114","article-title":"Neural networks with few multiplications","author":"Lin","year":"2015"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094626"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.01.010"},{"key":"ref117","article-title":"Trained ternary quantization","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Zhu"},{"key":"ref118","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref120","article-title":"Mixed precision quantization of convnets via differentiable neural architecture search","author":"Wu","year":"2018"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_1"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00242"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/mm.2020.3009475"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01566"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413631"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0134-0"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00273"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_16"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107647"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11623"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref133","first-page":"18 518","article-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","volume":"33","author":"Dong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref134","first-page":"11 875","article-title":"Hawq-v3: Dyadic neural network quantization","volume-title":"International Conference on Machine Learning","author":"Yao"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17269"},{"key":"ref136","first-page":"12 546","article-title":"Differentiable dynamic quantization with mixed precision and adaptive resolution","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref137","article-title":"Stochastic layer-wise precision in deep neural networks","author":"Lacey","year":"2018"},{"key":"ref138","article-title":"Mixed precision dnns: All you need is a good parametrization","volume-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020","author":"Uhlich"},{"key":"ref139","first-page":"5741","article-title":"Bayesian bits: Unifying quantization and pruning","volume":"33","author":"Van Baalen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/dac56929.2023.10247982"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref142","article-title":"Mobilevitv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features","author":"Wadekar","year":"2022"},{"key":"ref143","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20222"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref147","first-page":"34 451","article-title":"Q-vit: Accurate and fully quantized low-bit vision transformer","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02170"},{"key":"ref149","article-title":"Variation-aware vision transformer quantization","author":"Huang","year":"2023"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"ref151","article-title":"Easyquant: Post-training quantization via scale optimization","author":"Wu","year":"2020"},{"key":"ref152","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"ref154","article-title":"Symbolic music generation with diffusion models","author":"Mittal","year":"2021"},{"key":"ref155","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref156","article-title":"Permutation invariant graph generation via score-based generative modeling","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Niu"},{"key":"ref157","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref158","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"Chen","year":"2020"},{"key":"ref159","article-title":"Noise estimation for generative diffusion models","author":"San-Roman","year":"2021"},{"key":"ref160","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref161","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref162","article-title":"Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models","volume-title":"ICLR","author":"Bao"},{"key":"ref163","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref164","article-title":"Gotta go fast when generating data with score-based models","author":"Jolicoeur-Martineau","year":"2021"},{"key":"ref165","article-title":"Structural pruning for diffusion models","author":"Fang","year":"2023"},{"key":"ref166","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref168","article-title":"Towards accurate data-free quantization for diffusion models","author":"Wang","year":"2023"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"ref170","article-title":"Enhanced distribution alignment for post-training quantization of diffusion models","author":"Liu","year":"2024"},{"key":"ref171","article-title":"Degree-quant: Quantization-aware training for graph neural networks","author":"Tailor","year":"2020"},{"key":"ref172","first-page":"16 318","article-title":"Overcoming oscillations in quantization-aware training","volume-title":"International Conference on Machine Learning","author":"Nagel"},{"key":"ref173","article-title":"Ptqd: Accurate post-training quantization for diffusion models","author":"He","year":"2023"},{"key":"ref174","article-title":"Tfmq-dm: Temporal feature maintenance quantization for diffusion models","author":"Huang","year":"2023"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650109.pdf?arnumber=10650109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:01:03Z","timestamp":1725944463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":174,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650109","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}