{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:40:46Z","timestamp":1784302846557,"version":"3.55.0"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["Z2024-043"],"award-info":[{"award-number":["Z2024-043"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62404037"],"award-info":[{"award-number":["62404037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115830","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:18:53Z","timestamp":1774628333000},"page":"115830","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["HAQ-ViT: A hardware-aware post-training quantization for efficient vision transformer inference"],"prefix":"10.1016","volume":"342","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7208-7075","authenticated-orcid":false,"given":"Shiqi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haozu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sibo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changzeng","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4137-7272","authenticated-orcid":false,"given":"Mohamad","family":"Sawan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115830_bib0001","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0002","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.knosys.2026.115830_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112404","article-title":"Enhancing performance of transformer-based models in natural language understanding through word importance embedding","volume":"304","author":"Hong","year":"2024","journal-title":"Knowl. Based Syst."},{"issue":"1","key":"10.1016\/j.knosys.2026.115830_bib0004","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115830_bib0005","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0006","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: transformers for image recognition at scale, arXiv preprint arXiv: 2010.11929(2020)."},{"key":"10.1016\/j.knosys.2026.115830_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112531","article-title":"Adaptive class token knowledge distillation for efficient vision transformer","volume":"304","author":"Kang","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0008","series-title":"Low-power Computer Vision","first-page":"291","article-title":"A survey of quantization methods for efficient neural network inference","author":"Gholami","year":"2022"},{"key":"10.1016\/j.knosys.2026.115830_bib0009","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"9103","article-title":"Lgvit: dynamic early exiting for accelerating vision transformer","author":"Xu","year":"2023"},{"key":"10.1016\/j.knosys.2026.115830_bib0010","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.115830_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110953","article-title":"Deep internally connected transformer hashing for image retrieval","volume":"279","author":"Chao","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111562","article-title":"ASAFormer: Visual tracking with convolutional vision transformer and asymmetric selective attention","volume":"291","author":"Gong","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109552","article-title":"Vision transformers for dense prediction: a survey","volume":"253","author":"Zuo","year":"2022","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112181","article-title":"Polyp-LVT: polyp segmentation with lightweight vision transformers","volume":"300","author":"Lin","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0015","unstructured":"T. Dettmers, M. Lewis, Y. Belkada, L. Zettlemoyer, LLM.int8( ): 8-bit matrix multiplication for transformers at scale, ArXiv abs\/2208.07339(2022). https:\/\/api.semanticscholar.org\/CorpusID:251564521."},{"key":"10.1016\/j.knosys.2026.115830_bib0016","unstructured":"J. Choi, Z. Wang, S. Venkataramani, P.I.-J. Chuang, V. Srinivasan, K. Gopalakrishnan, Pact: Parameterized clipping activation for quantized neural networks, arXiv preprint arXiv: 1805.06085(2018)."},{"key":"10.1016\/j.knosys.2026.115830_bib0017","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"365","article-title":"Lq-nets: learned quantization for highly accurate and compact deep neural networks","author":"Zhang","year":"2018"},{"key":"10.1016\/j.knosys.2026.115830_bib0018","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume":"32","author":"Banner","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.knosys.2026.115830_bib0019","series-title":"2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)","first-page":"3009","article-title":"Low-bit quantization of neural networks for efficient inference","author":"Choukroun","year":"2019"},{"key":"10.1016\/j.knosys.2026.115830_bib0020","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Quantization and training of neural networks for efficient integer-Arithmetic-Only inference","author":"Jacob","year":"2018"},{"key":"10.1016\/j.knosys.2026.115830_bib0021","unstructured":"E. Frantar, S. Ashkboos, T. Hoefler, D. Alistarh, Gptq: Accurate post-training quantization for generative pre-trained transformers, arXiv preprint arXiv: 2210.17323(2022)."},{"key":"10.1016\/j.knosys.2026.115830_bib0022","series-title":"European Conference on Computer Vision","article-title":"PTQ4ViT: post-training quantization for vision transformers with twin uniform quantization","author":"Yuan","year":"2021"},{"key":"10.1016\/j.knosys.2026.115830_bib0023","article-title":"Towards accurate post-training quantization for vision transformer","author":"Ding","year":"2022","journal-title":"Proc. 30th ACM Int. Conf. Multimed."},{"key":"10.1016\/j.knosys.2026.115830_bib0024","series-title":"Neural Information Processing Systems","article-title":"Post-training quantization for vision transformer","author":"Liu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115830_bib0025","series-title":"International Joint Conference on Artificial Intelligence","article-title":"FQ-ViT: post-training quantization for fully quantized vision transformer","author":"Lin","year":"2021"},{"key":"10.1016\/j.knosys.2026.115830_bib0026","first-page":"17019","article-title":"I-ViT: integer-only quantization for efficient vision transformer inference","author":"Li","year":"2022","journal-title":"2023 IEEE\/CVF Int. Conf. Comput. Vision (ICCV)"},{"key":"10.1016\/j.knosys.2026.115830_bib0027","series-title":"Proceedings of the 61St ACM\/IEEE Design Automation Conference","article-title":"ViT-slice: end-to-end vision transformer accelerator with bit-slice algorithm","author":"Shin","year":"2024"},{"key":"10.1016\/j.knosys.2026.115830_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113246","article-title":"Asymmetric content-aided transformer for efficient image super-resolution","volume":"315","author":"Wang","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0029","unstructured":"R. Child, S. Gray, A. Radford, I. Sutskever, Generating long sequences with sparse transformers, arXiv preprint arXiv: 1904.10509(2019)."},{"key":"10.1016\/j.knosys.2026.115830_bib0030","series-title":"Advances in Neural Information Processing Systems","first-page":"13937","article-title":"DynamicViT: efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021"},{"key":"10.1016\/j.knosys.2026.115830_bib0031","article-title":"Not all patches are what you need: expediting vision transformers via token reorganizations","volume":"abs\/2202.07800","author":"Liang","year":"2022","journal-title":"ArXiv"},{"key":"10.1016\/j.knosys.2026.115830_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"22680","article-title":"SparsifiNer: learning sparse instance-Dependent attention for efficient vision transformers","author":"Wei","year":"2023"},{"key":"10.1016\/j.knosys.2026.115830_bib0033","unstructured":"I. Beltagy, M.E. Peters, A. Cohan, Longformer: the long-document transformer, arXiv preprint arXiv: 2004.05150(2020)."},{"key":"10.1016\/j.knosys.2026.115830_bib0034","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.knosys.2026.115830_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115830_bib0036","unstructured":"R. Wightman, PyTorch Image Models, 2019, 10.5281\/zenodo.4414861."},{"key":"10.1016\/j.knosys.2026.115830_bib0037","first-page":"20321","article-title":"NoisyQuant: noisy bias-enhanced post-training activation quantization for vision transformers","author":"Liu","year":"2022","journal-title":"2023 IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)"},{"key":"10.1016\/j.knosys.2026.115830_bib0038","article-title":"Quanttune: optimizing model quantization with adaptive outlier-driven fine tuning","volume":"abs\/2403.06497","author":"Chen","year":"2024","journal-title":"ArXiv"},{"key":"10.1016\/j.knosys.2026.115830_bib0039","first-page":"1","article-title":"TSPTQ-ViT: two-scaled post-training quantization for vision transformer","author":"Tai","year":"2023","journal-title":"ICASSP 2023 - 2023 IEEE Int. Conf. Acoustics, Speech Signal Process. (ICASSP)"},{"key":"10.1016\/j.knosys.2026.115830_bib0040","doi-asserted-by":"crossref","first-page":"1704","DOI":"10.1109\/TVLSI.2024.3422684","article-title":"P2-ViT: power-of-two post-training quantization and acceleration for fully quantized vision transformer","volume":"32","author":"Shi","year":"2024","journal-title":"IEEE Trans. Very Large Scale Integr. VLSI Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0041","doi-asserted-by":"crossref","first-page":"16932","DOI":"10.1109\/ICCV51070.2023.01557","article-title":"Jumping through local minima: quantization in the loss landscape of vision transformers","author":"Frumkin","year":"2023","journal-title":"2023 IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)"},{"key":"10.1016\/j.knosys.2026.115830_bib0042","article-title":"CPT-V: A contrastive approach to post-training quantization of vision transformers","volume":"abs\/2211.09643","author":"Frumkin","year":"2022","journal-title":"ArXiv"},{"key":"10.1016\/j.knosys.2026.115830_bib0043","first-page":"1","article-title":"Patch-wise mixed-precision quantization of vision transformer","author":"Xiao","year":"2023","journal-title":"2023 Int. Joint Conf. Neural Netw. (IJCNN)"},{"key":"10.1016\/j.knosys.2026.115830_bib0044","series-title":"European Conference on Computer Vision","article-title":"CLAMP-ViT: contrastive data-free learning for adaptive post-training quantization of ViTs","author":"Ramachandran","year":"2024"},{"key":"10.1016\/j.knosys.2026.115830_bib0045","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/FPL57034.2022.00027","article-title":"Auto-ViT-Acc: an FPGA-Aware automatic acceleration framework for vision transformer with mixed-scheme quantization","author":"Li","year":"2022","journal-title":"2022 32nd Int. Conf. Field-Programmable Logic Appl. (FPL)"},{"key":"10.1016\/j.knosys.2026.115830_bib0046","doi-asserted-by":"crossref","first-page":"17227","DOI":"10.1109\/TNNLS.2023.3301007","article-title":"PSAQ-ViT V2: toward accurate and general data-free quantization for vision transformers","volume":"35","author":"Li","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.115830_bib0047","article-title":"SaiT: sparse vision transformers through adaptive token pruning","volume":"abs\/2210.05832","author":"Li","year":"2022","journal-title":"ArXiv"},{"key":"10.1016\/j.knosys.2026.115830_bib0048","article-title":"Adaptive sparse ViT: towards learnable adaptive token pruning by fully exploiting self-attention","volume":"abs\/2209.13802","author":"Liu","year":"2022","journal-title":"ArXiv"},{"key":"10.1016\/j.knosys.2026.115830_bib0049","series-title":"Vision transformer pruning","author":"Zhu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115830_bib0050","first-page":"273","article-title":"ViTCoD: vision transformer acceleration via dedicated algorithm and accelerator co-Design","author":"You","year":"2022","journal-title":"2023 IEEE Int. Sympos. High-Perf. Computr Archit. (HPCA)"},{"key":"10.1016\/j.knosys.2026.115830_bib0051","series-title":"2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC)","first-page":"10","article-title":"1.1 Computing\u2019s energy problem (and what we can do about it)","author":"Horowitz","year":"2014"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005563?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005563?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:11:12Z","timestamp":1777569072000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126005563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":51,"alternative-id":["S0950705126005563"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115830","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HAQ-ViT: A hardware-aware post-training quantization for efficient vision transformer inference","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115830","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115830"}}