{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T04:12:39Z","timestamp":1748751159698,"version":"3.41.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031919787","type":"print"},{"value":"9783031919794","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-91979-4_10","type":"book-chapter","created":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:06:50Z","timestamp":1748718410000},"page":"97-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mixed Non-linear Quantization for\u00a0Vision Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8659-8518","authenticated-orcid":false,"given":"Gihwan","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9332-3508","authenticated-orcid":false,"given":"Jemin","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8244-4817","authenticated-orcid":false,"given":"Sihyeong","family":"Park","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2973-246X","authenticated-orcid":false,"given":"Yongin","family":"Kwon","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9615-1644","authenticated-orcid":false,"given":"Hyungshin","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"10_CR1","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Crandall, R.E., Pomerance, C.: Prime Numbers: A Computational Perspective, vol.\u00a02. Springer, New York (2005). https:\/\/doi.org\/10.1007\/0-387-28979-8","DOI":"10.1007\/0-387-28979-8"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Ding, Y., et al.: Towards accurate post-training quantization for vision transformer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5380\u20135388 (2022)","DOI":"10.1145\/3503161.3547826"},{"key":"10_CR4","unstructured":"Dong, P., et al.: PackQViT: faster sub-8-bit vision transformers via full and packed quantization on the mobile. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"10_CR5","unstructured":"Dong, Z., Yao, Z., Arfeen, D., Gholami, A., Mahoney, M.W., Keutzer, K.: HAWQ-V2: hessian aware trace-weighted quantization of neural networks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 18518\u201318529 (2020)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Dong, Z., Yao, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: HAWQ: hessian aware quantization of neural networks with mixed-precision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 293\u2013302 (2019)","DOI":"10.1109\/ICCV.2019.00038"},{"key":"10_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"10_CR8","unstructured":"Du, D., Gong, G., Chu, X.: Model quantization and hardware acceleration for vision transformers: a comprehensive survey. arXiv preprint arXiv:2405.00314 (2024)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M.W., Keutzer, K.: A survey of quantization methods for efficient neural network inference. In: Low-Power Computer Vision, pp. 291\u2013326. Chapman and Hall\/CRC (2022)","DOI":"10.1201\/9781003162810-13"},{"key":"10_CR10","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"10_CR11","unstructured":"Huang, X., Shen, Z., Cheng, K.T.: Variation-aware vision transformer quantization. arXiv preprint arXiv:2307.00331 (2023)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and 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 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"10_CR13","unstructured":"Kim, S., Gholami, A., Yao, Z., Mahoney, M.W., Keutzer, K.: I-BERT: integer-only BERT quantization. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 5506\u20135518. PMLR, 18\u201324 July 2021. https:\/\/proceedings.mlr.press\/v139\/kim21d.html"},{"key":"10_CR14","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bi-ViT: pushing the limit of vision transformer quantization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 3243\u20133251 (2024)","DOI":"10.1609\/aaai.v38i4.28109"},{"key":"10_CR16","unstructured":"Li, Y., Xu, S., Zhang, B., Cao, X., Gao, P., Guo, G.: Q-ViT: accurate and fully quantized low-bit vision transformer. In: Advances in Neural Information Processing Systems, vol. 35, pp. 34451\u201334463 (2022)"},{"key":"10_CR17","unstructured":"Li, Z., Yang, T., Wang, P., Cheng, J.: Q-ViT: fully differentiable quantization for vision transformer. arXiv preprint arXiv:2201.07703 (2022)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., Gu, Q.: I-ViT: integer-only quantization for efficient vision transformer inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17065\u201317075, October 2023","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Li, Z., Xiao, J., Yang, L., Gu, Q.: RepQ-ViT: scale reparameterization for post-training quantization of vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17227\u201317236 (2023)","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhang, T., Sun, P., Li, Z., Zhou, S.: FQ-ViT: post-training quantization for fully quantized vision transformer. In: International Joint Conference on Artificial Intelligence (2021). https:\/\/api.semanticscholar.org\/CorpusID:248300269","DOI":"10.24963\/ijcai.2022\/164"},{"key":"10_CR21","unstructured":"Liu, S.Y., Liu, Z., Cheng, K.T.: Oscillation-free quantization for low-bit vision transformers. In: International Conference on Machine Learning, pp. 21813\u201321824. PMLR (2023)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10_CR23","unstructured":"Liu, Z., Wang, Y., Han, K., Zhang, W., Ma, S., Gao, W.: Post-training quantization for vision transformer. In: Advances in Neural Information Processing Systems, vol. 34, pp. 28092\u201328103 (2021)"},{"key":"10_CR24","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8612\u20138620 (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, S., Sun, W., Sun, P., Liu, Y.: SOLE: hardware-software co-design of Softmax and LayerNorm for efficient transformer inference. In: 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD), pp.\u00a01\u20139. IEEE (2023)","DOI":"10.1109\/ICCAD57390.2023.10323725"},{"key":"10_CR27","unstructured":"Yao, Z., et\u00a0al.: HAWQ-V3: dyadic neural network quantization. In: International Conference on Machine Learning, pp. 11875\u201311886. PMLR (2021)"},{"key":"10_CR28","unstructured":"Yuan, Z., Zhou, R., Wang, H., He, L., Ye, Y., Sun, L.: ViT-1.58 B: mobile vision transformers in the 1-bit era. arXiv preprint arXiv:2406.18051 (2024)"},{"key":"10_CR29","doi-asserted-by":"publisher","unstructured":"Yuan, Z., Xue, C., Chen, Y., Wu, Q., Sun, G.: PTQ4ViT: post-training quantization for vision transformers with twin uniform quantization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13672, pp. 191\u2013207. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19775-8_12","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"10_CR30","unstructured":"Zhang, Z., He, B., Zhang, Z.: Practical edge kernels for integer-only vision transformers under post-training quantization. In: Proceedings of Machine Learning and Systems, vol. 5, pp. 35\u201347 (2023)"},{"key":"10_CR31","unstructured":"Zhong, Y., Hu, J., Huang, Y., Zhang, Y., Ji, R.: ERQ: error reduction for post-training quantization of vision transformers. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"10_CR32","unstructured":"Zhong, Y., Hu, J., Lin, M., Chen, M., Ji, R.: I &S-ViT: an inclusive & stable method for pushing the limit of post-training ViTS quantization. arXiv preprint arXiv:2311.10126 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91979-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:06:59Z","timestamp":1748718419000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91979-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919787","9783031919794"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91979-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}