{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T23:50:07Z","timestamp":1758325807491,"version":"3.44.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2022YFC3602601"],"award-info":[{"award-number":["2022YFC3602601"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Experimental Technology Reaseach Project of Zhejiang University","award":["SYBJS202314"],"award-info":[{"award-number":["SYBJS202314"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10489-025-06418-0","type":"journal-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T21:20:22Z","timestamp":1743542422000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards accurate post-training quantization for reparameterized models"],"prefix":"10.1007","volume":"55","author":[{"given":"Luoming","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yefei","family":"He","sequence":"additional","affiliation":[]},{"given":"Wen","family":"Fei","sequence":"additional","affiliation":[]},{"given":"Zhenyu","family":"Lou","sequence":"additional","affiliation":[]},{"given":"Weijia","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yangwei","family":"Ying","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1314-8883","authenticated-orcid":false,"given":"Hong","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,31]]},"reference":[{"key":"6418_CR1","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W et\u00a0al (2022) Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976"},{"key":"6418_CR2","doi-asserted-by":"crossref","unstructured":"Wang Y (2022) Edge-enhanced feature distillation network for efficient super-resolution. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 777\u2013785","DOI":"10.1109\/CVPRW56347.2022.00093"},{"issue":"9","key":"6418_CR3","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13048","volume":"39","author":"P Theerthagiri","year":"2022","unstructured":"Theerthagiri P, Ruby AU (2022) Rffs: Recursive random forest feature selection based ensemble algorithm for chronic kidney disease prediction. Expert Syst 39(9):e13048","journal-title":"Expert Syst"},{"key":"6418_CR4","unstructured":"Esser SK, McKinstry JL, Bablani D, Appuswamy R, Modha DS (2020) Learned step size quantization. In Int Conf Learn Rep"},{"key":"6418_CR5","unstructured":"Nagel M, Amjad RA, van Baalen M, Louizos C, Blankevoort T (2020) Up or down? adaptive rounding for post-training quantization. arXiv preprint arXiv:2004.10568"},{"key":"6418_CR6","unstructured":"LeCun Y, Denker J, Solla S (1989) Optimal brain damage. Adv Neural Inf Process Syst 2"},{"key":"6418_CR7","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531"},{"key":"6418_CR8","unstructured":"Zagoruyko S, Komodakis N (2017) Diracnets: Training very deep neural networks without skip-connections. arXiv preprint arXiv:1706.00388"},{"key":"6418_CR9","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang X, Han J, Ding G (2021) Diverse branch block: Building a convolution as an inception-like unit. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10886\u201310895","DOI":"10.1109\/CVPR46437.2021.01074"},{"key":"6418_CR10","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang X, Ma N, Han J, Ding G, Sun J (2021) Repvgg: Making vgg-style convnets great again. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13733\u201313742","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"6418_CR11","unstructured":"Anasosalu Vasu PK, Gabriel J, Zhu J, Tuzel O, Ranjan A (2022) An improved one millisecond mobile backbone. arXiv preprint arXiv:2206.04040"},{"key":"6418_CR12","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"6418_CR13","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HY (2023) Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"6418_CR14","doi-asserted-by":"crossref","unstructured":"Zhang X, Zeng H, Zhang L (2021) Edge-oriented convolution block for real-time super resolution on mobile devices. In Proceedings of the 29th ACM international conference on multimedia, pp 4034\u20134043","DOI":"10.1145\/3474085.3475291"},{"key":"6418_CR15","doi-asserted-by":"crossref","unstructured":"Bhalgat Y, Lee J, Nagel M, Blankevoort T, Kwak N (2020) Lsq+: Improving low-bit quantization through learnable offsets and better initialization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 696\u2013697","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"6418_CR16","unstructured":"Li Y, Gong R, Tan X, Yang Y, Hu P, Zhang Q, Yu F, Wang W, Gu S (2021) Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426"},{"key":"6418_CR17","first-page":"448","volume-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"S Ioffe","year":"2015","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, PMLR, pp 448\u2013456"},{"key":"6418_CR18","unstructured":"Ding X, Chen H, Zhang X, Huang K, Han J, Ding G (2022) Re-parameterizing your optimizers rather than architectures. arXiv preprint arXiv:2205.15242"},{"key":"6418_CR19","unstructured":"Chu X, Li L, Zhang B (2022) Make repvgg greater again: A quantization-aware approach. arXiv preprint arXiv:2212.01593"},{"key":"6418_CR20","doi-asserted-by":"crossref","unstructured":"Ding X, Guo Y, Ding G, Han J (2019) Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks. In Proceedings of the IEEE\/CVF international conference on computer vision, pp 1911\u20131920","DOI":"10.1109\/ICCV.2019.00200"},{"key":"6418_CR21","doi-asserted-by":"crossref","unstructured":"Hu M, Feng J, Hua J, Lai B, Huang J, Gong X, Hua XS (2022) Online convolutional re-parameterization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 568\u2013577","DOI":"10.1109\/CVPR52688.2022.00065"},{"key":"6418_CR22","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang X, Han J, Ding G (2022) Scaling up your kernels to 31x31: Revisiting large kernel design in cnns. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11963\u201311975","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"6418_CR23","unstructured":"Ding X, Xia C, Zhang X, Chu X, Han J, Ding G (2021) Repmlp: Re-parameterizing convolutions into fully-connected layers for image recognition. arXiv preprint arXiv:2105.01883"},{"key":"6418_CR24","doi-asserted-by":"crossref","unstructured":"Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, Adam H, Kalenichenko D (2018) Quantization training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2704\u20132713","DOI":"10.1109\/CVPR.2018.00286"},{"key":"6418_CR25","unstructured":"Fan A, Stock P, Graham B, Grave E, Gribonval R, Jegou H, Joulin A (2020) Training with quantization noise for extreme model compression. arXiv preprint arXiv:2004.07320"},{"issue":"6","key":"6418_CR26","doi-asserted-by":"publisher","first-page":"6266","DOI":"10.1007\/s10489-022-03691-1","volume":"53","author":"L Zhang","year":"2023","unstructured":"Zhang L, He Y, Lou Z, Ye X, Wang Y, Zhou H (2023) Root quantization: a self-adaptive supplement ste. Appl Intell 53(6):6266\u20136275","journal-title":"Appl Intell"},{"key":"6418_CR27","unstructured":"Banner R, Nahshan Y, Soudry D (2019) Post training 4-bit quantization of convolutional networks for rapid-deployment. In Advances in Neural Information Processing Systems"},{"key":"6418_CR28","doi-asserted-by":"crossref","unstructured":"Choukroun Y, Kravchik E, Yang F, Kisilev P (2019) Low-bit quantization of neural networks for efficient inference. In 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW), IEEE, pp 3009\u20133018","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"6418_CR29","doi-asserted-by":"crossref","unstructured":"Nagel M, van Baalen M, Blankevoort T, Welling M (2019) Data-free quantization through weight equalization bias correction. In Proceedings of the IEEE\/CVF international conference on computer vision, pp 1325\u20131334","DOI":"10.1109\/ICCV.2019.00141"},{"key":"6418_CR30","first-page":"9847","volume-title":"Towards accurate post-training network quantization via bit-split and stitching","author":"P Wang","year":"2020","unstructured":"Wang P, Chen Q, He X, Cheng J (2020) Towards accurate post-training network quantization via bit-split and stitching. In international conference on machine learning, PMLR, pp 9847\u20139856"},{"key":"6418_CR31","unstructured":"Wu D, Tang Q, Zhao Y, Zhang M, Fu Y, Zhang D (2020) Easyquant: Post-training quantization via scale optimization. arXiv preprint arXiv:2006.16669"},{"key":"6418_CR32","unstructured":"Hubara I, Nahshan Y, Hanani Y, Banner R, Soudry D (2021) Accurate post training quantization with small calibration sets. In international conference on machine learning, PMLR, pp 4466\u20134475"},{"key":"6418_CR33","unstructured":"Bengio Y, L\u00e9onard N, Courville A (2013) Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432"},{"key":"6418_CR34","unstructured":"Wei X, Gong R, Li Y, Liu X, Yu F (2022) Qdrop: Randomly dropping quantization for extremely low-bit post-training quantization. arXiv preprint arXiv:2203.05740"},{"key":"6418_CR35","first-page":"4475","volume":"35","author":"E Frantar","year":"2022","unstructured":"Frantar E, Alistarh D (2022) Optimal brain compression: A framework for accurate post-training quantization pruning. Adv Neural Inf Process Syst 35:4475\u20134488","journal-title":"Adv Neural Inf Process Syst"},{"key":"6418_CR36","first-page":"293","volume-title":"Optimal brain surgeon general network pruning","author":"B Hassibi","year":"1993","unstructured":"Hassibi B, Stork DG, Wolff GJ (1993) Optimal brain surgeon general network pruning. In IEEE international conference on neural networks, IEEE, pp 293\u2013299"},{"key":"6418_CR37","unstructured":"Zhang S, Roller S, Goyal N, Artetxe M, Chen M, Chen S, Dewan C, Diab M, Li X, Lin XV et\u00a0al (2022) Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068"},{"key":"6418_CR38","unstructured":"Workshop B, Scao TL, Fan A, Akiki C, Pavlick E, Ili\u0107 S, Hesslow D, Castagn\u00e9 R, Luccioni AS, Yvon F et\u00a0al (2022) Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100"},{"key":"6418_CR39","first-page":"17402","volume":"35","author":"X Wei","year":"2022","unstructured":"Wei X, Zhang Y, Zhang X, Gong R, Zhang S, Zhang Q, Yu F, Liu X (2022) Outlier suppression: Pushing the limit of low-bit transformer language models. Adv Neural Inf Process Syst 35:17402\u201317414","journal-title":"Adv Neural Inf Process Syst"},{"key":"6418_CR40","first-page":"30318","volume":"35","author":"T Dettmers","year":"2022","unstructured":"Dettmers T, Lewis M, Belkada Y, Zettlemoyer L (2022) Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. Adv Neural Inf Process Syst 35:30318\u201330332","journal-title":"Adv Neural Inf Process Syst"},{"key":"6418_CR41","unstructured":"Xiao G, Lin J, Seznec M, Demouth J, Han S (2022) Smoothquant: Accurate efficient post-training quantization for large language models. arXiv preprint arXiv:2211.10438"},{"issue":"1","key":"6418_CR42","doi-asserted-by":"publisher","first-page":"74","DOI":"10.2307\/3001634","volume":"9","author":"WJ Dixon","year":"1953","unstructured":"Dixon WJ (1953) Processing data for outliers. Biometrics 9(1):74\u201389","journal-title":"Biometrics"},{"key":"6418_CR43","first-page":"1074","volume":"34","author":"H Bai","year":"2021","unstructured":"Bai H, Cao M, Huang P, Shan J (2021) Batchquant: Quantized-for-all architecture search with robust quantizer. Adv Neural Inf Process Syst 34:1074\u20131085","journal-title":"Adv Neural Inf Process Syst"},{"key":"6418_CR44","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision pattern recognition, IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6418_CR45","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"3","key":"6418_CR46","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins H, Monro S (1951) A stochastic approximation method. Ann Math Stat 22(3):400\u2013407","journal-title":"Ann Math Stat"},{"key":"6418_CR47","doi-asserted-by":"crossref","unstructured":"He K, X Z, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06418-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06418-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06418-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:34:33Z","timestamp":1758310473000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06418-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":47,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["6418"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06418-0","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,3,31]]},"assertion":[{"value":"26 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"606"}}