{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:12:47Z","timestamp":1789038767678,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374639","type":"print"},{"value":"9783032374646","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37464-6_21","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:51:27Z","timestamp":1789037487000},"page":"385-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BLOB-Q: Boosting Low Bit ViT Quantization via\u00a0Global Optimization on\u00a0Model Distortion"],"prefix":"10.1007","author":[{"given":"Zhe","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fen","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed M. Sabry","family":"Aly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"21_CR1","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D.: Post-training 4-bit quantization of convolution networks for rapid. arXiv:1810.05723 -deployment. arXiv preprint (2018)"},{"key":"21_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109780","volume":"143","author":"J Chen","year":"2023","unstructured":"Chen, J., Bai, S., Huang, T., Wang, M., Tian, G., Liu, Y.: Data-free quantization via mixed-precision compensation without fine-tuning. Patt. Recogn. 143, 109780 (2023)","journal-title":"Patt. Recogn."},{"key":"21_CR3","unstructured":"Wu, D., Tang, Q., Y.Z.M.Z.D.Z.Y.F.: Easyquant: post-training quantization via scale optimization (2020)"},{"key":"21_CR4","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":"21_CR5","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. arXiv (2019)","DOI":"10.1109\/ICCV.2019.00038"},{"key":"21_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"21_CR7","doi-asserted-by":"publisher","first-page":"4475","DOI":"10.52202\/068431-0323","volume":"35","author":"E Frantar","year":"2022","unstructured":"Frantar, E., Alistarh, D.: Optimal brain compression: a framework for accurate post-training quantization and pruning. Adv. Neural. Inf. Process. Syst. 35, 4475\u20134488 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Geng, X., et\u00a0al.: From algorithm to hardware: a survey on efficient and safe deployment of deep neural networks. IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TNNLS.2024.3394494"},{"key":"21_CR10","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. arXiv:1506.02626 arXiv preprint (2015)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask r-CNN. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"21_CR12","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Quantized neural networks: training neural networks with low precision weights and activations. arXiv:1609.07061 (2016)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Li, F.F.: Perceptual losses for real-time style transfer and super-resolution. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"21_CR14","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Kim, M., Lee, J., Kim, J., Yun, J., Kwon, Y., Kang, U.: Lampq: towards accurate layer-wise mixed precision quantization for vision transformers. In: The 40th Annual AAAI Conference on Artificial Intelligence (2026)","DOI":"10.1609\/aaai.v40i7.37489"},{"key":"21_CR16","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Kurtic, E., et al.: The optimal Bert surgeon: scalable and accurate second-order pruning for large language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 4163\u20134181 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Li, R., Wang, Y., Liang, F., Qin, H., Yan, J., Fan, R.: Fully quantized network for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2810\u20132819 (2019)","DOI":"10.1109\/CVPR.2019.00292"},{"key":"21_CR19","unstructured":"Li, Y., et al.: BRECQ: pushing the limit of post-training quantization by block reconstruction. In: International Conference on Learning Representations (2020)"},{"key":"21_CR20","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, pp. 17065\u201317075 (2023)","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"21_CR21","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":"21_CR22","unstructured":"Lin, J., et al.: Awq: activation-aware weight quantization for on-device llm compression and acceleration. In: Proceedings of machine learning and systems vol. 6, pp. 87\u2013100 (2024)"},{"key":"21_CR23","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. arXiv:2111.13824 arXiv preprint (2021)","DOI":"10.24963\/ijcai.2022\/164"},{"key":"21_CR24","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: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp. 1173\u20131179 (2022)","DOI":"10.24963\/ijcai.2022\/164"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yang, H., Dong, Z., Keutzer, K., Du, L., Zhang, S.: Noisyquant: noisy bias-enhanced post-training activation quantization for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20321\u201320330 (2023)","DOI":"10.1109\/CVPR52729.2023.01946"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yang, H., Dong, Z., Keutzer, K., Du, L., Zhang, S.: Noisyquant: noisy bias-enhanced post-training activation quantization for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20321\u201320330 (2023)","DOI":"10.1109\/CVPR52729.2023.01946"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR28","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":"21_CR29","first-page":"28092","volume":"34","author":"Z Liu","year":"2021","unstructured":"Liu, Z., Wang, Y., Han, K., Zhang, W., Ma, S., Gao, W.: Post-training quantization for vision transformer. Adv. Neural. Inf. Process. Syst. 34, 28092\u201328103 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR30","unstructured":"Lou, Q., Guo, F., Kim, M., Liu, L., Jiang, L.: Autoq: automated kernel-wise neural network quantizations. In: ICLR (2020)"},{"key":"21_CR31","unstructured":"Nagel, M., Amjad, R.A., Baalen, M.V., Louizos, C., Blankevoort, T.: Up or down? adaptive rounding for post-training quantization. PMLR (2020)"},{"key":"21_CR32","unstructured":"Nagel, M., Amjad, R.A., Van Baalen, M., Louizos, C., Blankevoort, T.: Up or down? adaptive rounding for post-training quantization. In: International Conference on Machine Learning, pp. 7197\u20137206. PMLR (2020)"},{"key":"21_CR33","doi-asserted-by":"publisher","unstructured":"Nahshan, Y., et al.: Loss aware post-training quantization. Mach. Learn., 3245\u20133262 (2021). https:\/\/doi.org\/10.1007\/s10994-021-06053-z","DOI":"10.1007\/s10994-021-06053-z"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-NET: imagenet classification using binary convolutional neural networks. In: arXiv preprint. arXiv:1603.05279 (2016)","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Shi, H., Cheng, X., Mao, W., Wang, Z.: P$$^2$$-vit: power-of-two post-training quantization and acceleration for fully quantized vision transformer. IEEE Trans. Very Large Scale Integration (VLSI) Syst. (2024)","DOI":"10.1109\/TVLSI.2024.3422684"},{"key":"21_CR36","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"key":"21_CR37","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":"21_CR38","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":"21_CR39","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"21_CR40","unstructured":"Wu, D., Tang, Q., Zhao, Y., Zhang, M., Fu, Y., Zhang, D.: Easyquant: post-training quantization via scale optimization. arXiv preprint arXiv:2006.16669 (2020)"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, S., Zhang, J., Chen, J., Wang, Y.: Fima-q: post-training quantization for vision transformers by fisher information matrix approximation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.01387"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zhang, J., Chen, J., Guo, J., Huang, D., Wang, Y.: Aphq-vit: post-training quantization with average perturbation hessian based reconstruction for vision transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.00905"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Xiao, J., Li, Z., Yang, L., Gu, Q.: Patch-wise mixed-precision quantization of vision transformer. In: 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. IEEE (2023)","DOI":"10.1109\/IJCNN54540.2023.10191205"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Xu, K., et al.: Lpvit: low-power semi-structured pruning for vision transformers. In: European Conference on Computer Vision, pp. 269\u2013287. Springer (2024)","DOI":"10.1007\/978-3-031-73209-6_16"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Xu, K., Li, Z., Wang, S., Zhang, X.: PTMQ: post-training multi-bit quantization of neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 16193\u201316201 (2024)","DOI":"10.1609\/aaai.v38i14.29553"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Yang, L., Jin, Q.: Fracbits: mixed precision quantization via fractional bit-widths. arXiv:2007.02017 arXiv preprint (2020)","DOI":"10.1609\/aaai.v35i12.17269"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Xue, C., Chen, Y., Wu, Q., Sun, G.: Ptq4vit: post-training quantization framework for vision transformers with twin uniform quantization. arXiv:2111.12293 arXiv preprint (2021)","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Xue, C., Chen, Y., Wu, Q., Sun, G.: Ptq4vit: post-training quantization for vision transformers with twin uniform quantization. In: European Conference on Computer Vision, pp. 191\u2013207. Springer (2022)","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yang, J., Ye, D., Hua, G.: Lq-nets: learned quantization for highly accurate and compact deep neural networks. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"21_CR50","unstructured":"Zhao, R., Hu, Y., Dotzel, J., Sa, C.D., Zhang, Z.: Improving neural network quantization without retraining using outlier channel splitting. PMLR (2019)"},{"key":"21_CR51","unstructured":"Zhong, Y., Hu, J., Huang, Y., Zhang, Y., Ji, R.: ERQ: error reduction for post-training quantization of vision transformers. In: Proceedings of the International Conference on Machine Learning (ICML) (2024)"},{"key":"21_CR52","unstructured":"Zhou, A., Yao, A., Guo, Y., Xu, L., Chen, Y.: Incremental network quantization: towards lossless CNNs with low-precision weights. arXiv:1702.03044 arXiv preprint (2017)"},{"key":"21_CR53","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: Dorefa-net: training low bitwidth convolutional neural networks with low bitwidth gradients. In: arXiv preprint arXiv:1606.06160 (2016)"},{"key":"21_CR54","unstructured":"Zhu, C., Han, S., Mao, H., Dally, W.: Ternary weight networks. In: ICLR (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37464-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:51:55Z","timestamp":1789037515000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37464-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374639","9783032374646"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37464-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}