{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T01:40:13Z","timestamp":1743385213969,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819628636","type":"print"},{"value":"9789819628643","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\/978-981-96-2864-3_34","type":"book-chapter","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T01:15:22Z","timestamp":1743383722000},"page":"430-441","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Gradient-Aware Incremental Network Quantization"],"prefix":"10.1007","author":[{"given":"Jiao","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoliu","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"34_CR1","unstructured":"Banner, R., Nahshan, Y., Soudry, D.: Post training 4-bit quantization of convolutional networks for rapid-deployment. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"34_CR2","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned step size quantization. arXiv preprint arXiv:1902.08153 (2019)"},{"key":"34_CR3","first-page":"4475","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":"34_CR4","doi-asserted-by":"crossref","unstructured":"Gong, R., et al.: Differentiable soft quantization: bridging full-precision and low-bit neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4852\u20134861 (2019)","DOI":"10.1109\/ICCV.2019.00495"},{"key":"34_CR5","unstructured":"Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: International Conference on Machine Learning, pp. 1737\u20131746. PMLR (2015)"},{"key":"34_CR6","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)"},{"key":"34_CR7","unstructured":"Hubara, I., Nahshan, Y., Hanani, Y., Banner, R., Soudry, D.: Accurate post training quantization with small calibration sets. In: International Conference on Machine Learning, pp. 4466\u20134475. PMLR (2021)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Jung, S., et al.: Learning to quantize deep networks by optimizing quantization intervals with task loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4350\u20134359 (2019)","DOI":"10.1109\/CVPR.2019.00448"},{"key":"34_CR9","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"issue":"11","key":"34_CR10","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Ding, W., Liu, C., Zhang, B., Guo, G.: TRQ: ternary neural networks with residual quantization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 8538\u20138546 (2021)","DOI":"10.1609\/aaai.v35i10.17036"},{"key":"34_CR12","unstructured":"Li, Y., Dong, X., Wang, W.: Additive powers-of-two quantization: an efficient non-uniform discretization for neural networks. accepted by ICLR, arXiv preprint arXiv:1909.13144 (2020)"},{"key":"34_CR13","unstructured":"Li, Y., et al.: Brecq: pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426 (2021)"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Cheng, K.T., Huang, D., Xing, E., Shen, Z.: Nonuniform-to-uniform quantization: towards accurate quantization via generalized straight-through estimation (2022)","DOI":"10.1109\/CVPR52688.2022.00489"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z.G., Mattina, M.: Learning low-precision neural networks without straight-through estimator (STE). arXiv preprint arXiv:1903.01061 (2019)","DOI":"10.24963\/ijcai.2019\/425"},{"key":"34_CR16","unstructured":"Miyashita, D., Lee, E.H., Murmann, B.: Convolutional neural networks using logarithmic data representation. arXiv preprint arXiv:1603.01025 (2016)"},{"key":"34_CR17","unstructured":"Nagel, M., Amjad, R.A., Van\u00a0Baalen, 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)"},{"issue":"3","key":"34_CR18","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1109\/TPAMI.2018.2884462","volume":"42","author":"A Rosenfeld","year":"2018","unstructured":"Rosenfeld, A., Tsotsos, J.K.: Incremental learning through deep adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 42(3), 651\u2013663 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR19","unstructured":"Wu, Y., et al.: Incremental classifier learning with generative adversarial networks. arXiv preprint arXiv:1802.00853 (2018)"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, Y., Zhou, A., Lin, W., Xiong, H.: Deep neural network compression with single and multiple level quantization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11663"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Yamamoto, K.: Learnable companding quantization for accurate low-bit neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5029\u20135038 (2021)","DOI":"10.1109\/CVPR46437.2021.00499"},{"key":"34_CR22","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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 365\u2013382 (2018)","DOI":"10.1007\/978-3-030-01237-3_23"},{"issue":"2","key":"34_CR23","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1137\/22M1511709","volume":"5","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Zhou, Y., Saab, R.: Post-training quantization for neural networks with provable guarantees. SIAM J. Math. Data Sci. 5(2), 373\u2013399 (2023)","journal-title":"SIAM J. Math. Data Sci."},{"key":"34_CR24","unstructured":"Zhou, A., Yao, A., Guo, Y., Xu, L., Chen, Y.: Incremental network quantization: towards lossless CNNs with low-precision weights. arXiv preprint arXiv:1702.03044 (2017)"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Shen, C., Tan, M., Liu, L., Reid, I.: Towards effective low-bitwidth convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7920\u20137928 (2018)","DOI":"10.1109\/CVPR.2018.00826"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2864-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T01:15:30Z","timestamp":1743383730000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2864-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819628636","9789819628643"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2864-3_34","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":"29 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"7 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}