{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:53:08Z","timestamp":1771955588079,"version":"3.50.1"},"publisher-location":"Cham","reference-count":53,"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_13","type":"book-chapter","created":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:06:56Z","timestamp":1748718416000},"page":"150-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["EPTQ: Enhanced Post-training Quantization via\u00a0Hessian-Guided Network-Wise Optimization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0925-7767","authenticated-orcid":false,"given":"Ofir","family":"Gordon","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1868-9243","authenticated-orcid":false,"given":"Elad","family":"Cohen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5612-6348","authenticated-orcid":false,"given":"Hai Victor","family":"Habi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5339-9439","authenticated-orcid":false,"given":"Arnon","family":"Netzer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"issue":"2","key":"13_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1944345.1944349","volume":"58","author":"H Avron","year":"2011","unstructured":"Avron, H., Toledo, S.: Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix. J. ACM (JACM) 58(2), 1\u201334 (2011)","journal-title":"J. ACM (JACM)"},{"key":"13_CR2","unstructured":"Banner, R., Hubara, I., Hoffer, E., Soudry, D.: Scalable methods for 8-bit training of neural networks. NeurIPS 31 (2018)"},{"key":"13_CR3","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D.: Post-training 4-bit quantization of convolution networks for rapid-deployment. arXiv preprint arXiv:1810.05723 (2018)"},{"key":"13_CR4","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D.: ACIQ: analytical clipping for integer quantization of neural networks. In: ICLR (2019)"},{"key":"13_CR5","unstructured":"Botev, A., Ritter, H., Barber, D.: Practical gauss-newton optimisation for deep learning. In: ICML, pp. 557\u2013565. PMLR (2017)"},{"key":"13_CR6","unstructured":"Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: train one network and specialize it for efficient deployment. In: ICLR (2019)"},{"key":"13_CR7","unstructured":"Cai, H., Zhu, L., Han, S.: Proxylessnas: direct neural architecture search on target task and hardware. In: ICLR (2018)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV, pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Choukroun, Y., Kravchik, E., Yang, F., Kisilev, P.: Low-bit quantization of neural networks for efficient inference. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 3009\u20133018. IEEE (2019)","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"13_CR10","unstructured":"Dong, X., Chen, S., Pan, S.: Learning to prune deep neural networks via layer-wise optimal brain surgeon. NeurIPS 30 (2017)"},{"key":"13_CR11","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: NeurIPS, pp. 18518\u201318529 (2020)"},{"key":"13_CR12","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: ICCV, pp. 293\u2013302 (2019)","DOI":"10.1109\/ICCV.2019.00038"},{"key":"13_CR13","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned step size quantization. In: ICLR (2020)"},{"key":"13_CR14","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: ICLR (2021)"},{"key":"13_CR15","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. arXiv preprint arXiv:2103.13630 (2021)","DOI":"10.1201\/9781003162810-13"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Gholami, A., et al.: Squeezenext: hardware-aware neural network design. In: CVPR, pp. 1638\u20131647 (2018)","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"13_CR17","unstructured":"Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: ICML, pp. 1737\u20131746. PMLR (2015)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Habi, H.V., Jennings, R.H., Netzer, A.: Hmq: hardware friendly mixed precision quantization block for CNNs. In: ECCV, pp. 448\u2013463 (2020)","DOI":"10.1007\/978-3-030-58574-7_27"},{"key":"13_CR19","unstructured":"Habi, H.V., et al.: HPTQ: hardware-friendly post training quantization. arXiv preprint arXiv:2109.09113 (2021)"},{"key":"13_CR20","unstructured":"Hassibi, B., Stork, D.: Second order derivatives for network pruning: Optimal brain surgeon. NeurIPS 5 (1992)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"He, Y., Lin, J., Liu, Z., Wang, H., Li, L.J., Han, S.: Amc: automl for model compression and acceleration on mobile devices. In: ECCV, pp. 784\u2013800 (2018)","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"13_CR23","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"13_CR24","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, N.: Data-driven sparse structure selection for deep neural networks. In: ECCV, pp. 304\u2013320 (2018)","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"13_CR26","unstructured":"Hubara, I., Nahshan, Y., Hanani, Y., Banner, R., Soudry, D.: Accurate post training quantization with small calibration sets. In: ICML, pp. 4466\u20134475. PMLR (2021)"},{"key":"13_CR27","unstructured":"Hubara, I., Nahshan, Y., Hanani, Y., Banner, R., Soudry, D.: Improving post training neural quantization: Layer-wise calibration and integer programming. In: ICLR (2021)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: CVPR, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Jeon, Y., Lee, C., Kim, H.y.: Genie: show me the data for quantization. arXiv preprint arXiv:2212.04780 (2022)","DOI":"10.1109\/CVPR52729.2023.01161"},{"key":"13_CR30","first-page":"20415","volume":"33","author":"J Kim","year":"2020","unstructured":"Kim, J., Yoo, K., Kwak, N.: Position-based scaled gradient for model quantization and pruning. NeurIPS 33, 20415\u201320426 (2020)","journal-title":"NeurIPS"},{"key":"13_CR31","unstructured":"Li, Y., et al.: BRECQ: pushing the limit of post-training quantization by block reconstruction. In: ICLR (2021)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Liu, J., Niu, L., Yuan, Z., Yang, D., Wang, X., Liu, W.: Pd-quant: post-training quantization based on prediction difference metric. In: CVPR, pp. 24427\u201324437 (2023)","DOI":"10.1109\/CVPR52729.2023.02340"},{"key":"13_CR34","unstructured":"Liu, L., et al.: On the variance of the adaptive learning rate and beyond. In: ICLR (2019)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Solving oscillation problem in post-training quantization through a theoretical perspective. In: ICCV, pp. 7950\u20137959 (2023)","DOI":"10.1109\/CVPR52729.2023.00768"},{"key":"13_CR36","unstructured":"Mishra, A., Marr, D.: Apprentice: using knowledge distillation techniques to improve low-precision network accuracy. In: ICML. PMLR (2018)"},{"key":"13_CR37","unstructured":"Nagel, M., Amjad, R.A., Van\u00a0Baalen, M., Louizos, C., Blankevoort, T.: Up or down? adaptive rounding for post-training quantization. In: ICML, pp. 7197\u20137206. PMLR (2020)"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Nagel, M., Baalen, M.v., Blankevoort, T., Welling, M.: Data-free quantization through weight equalization and bias correction. In: ICCV, pp. 1325\u20131334 (2019)","DOI":"10.1109\/ICCV.2019.00141"},{"key":"13_CR39","unstructured":"Nagel, M., Fournarakis, M., Bondarenko, Y., Blankevoort, T.: Overcoming oscillations in quantization-aware training. arXiv preprint arXiv:2203.11086 (2022)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Nahshan, Y., et al.: Loss aware post-training quantization. Mach. Learn. 110(11), 3245\u20133262 (2021)","DOI":"10.1007\/s10994-021-06053-z"},{"key":"13_CR41","unstructured":"Polino, A., Pascanu, R., Alistarh, D.: Model compression via distillation and quantization. In: ICLR (2018)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: CVPR, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Shen, S., et al.: Q-bert: hessian based ultra low precision quantization of bert. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 8815\u20138821 (2020)","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"13_CR45","unstructured":"Wei, X., Gong, R., Li, Y., Liu, X., Yu, F.: QDrop: randomly dropping quantization for extremely low-bit post-training quantization. In: ICLR (2021)"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Wong, A., Famuori, M., Shafiee, M.J., Li, F., Chwyl, B., Chung, J.: Yolo nano: a highly compact you only look once convolutional neural network for object detection. In: 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing-NeurIPS Edition (EMC2-NIPS), pp. 22\u201325. IEEE (2019)","DOI":"10.1109\/EMC2-NIPS53020.2019.00013"},{"key":"13_CR47","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":"13_CR48","doi-asserted-by":"crossref","unstructured":"Yao, H., Li, P., Cao, J., Liu, X., Xie, C., Wang, B.: RAPQ: rescuing accuracy for power-of-two low-bit post-training quantization. arXiv preprint arXiv:2204.12322 (2022)","DOI":"10.24963\/ijcai.2022\/219"},{"key":"13_CR49","unstructured":"Yao, Z., et\u00a0al.: Hawq-v3: Dyadic neural network quantization. In: ICML, pp. 11875\u201311886. PMLR (2021)"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Yao, Z., Gholami, A., Keutzer, K., Mahoney, M.W.: Pyhessian: eural networks through the lens of the hessian. In: IEEE International Conference on Big Data, pp. 581\u2013590 (2020)","DOI":"10.1109\/BigData50022.2020.9378171"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Yu, S., et al.: Hessian-aware pruning and optimal neural implant. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3880\u20133891 (2022)","DOI":"10.1109\/WACV51458.2022.00372"},{"key":"13_CR52","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: ECCV, pp. 191\u2013207 (2022)","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"13_CR53","first-page":"6666","volume":"35","author":"D Zheng","year":"2022","unstructured":"Zheng, D., Liu, Y., Li, L., et al.: Leveraging inter-layer dependency for post-training quantization. NeurIPS 35, 6666\u20136679 (2022)","journal-title":"NeurIPS"}],"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_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:07:11Z","timestamp":1748718431000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91979-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919787","9783031919794"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91979-4_13","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"}}]}}