{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:02:03Z","timestamp":1757620923265,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031937088"},{"type":"electronic","value":"9783031937095"}],"license":[{"start":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T00:00:00Z","timestamp":1754092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T00:00:00Z","timestamp":1754092800000},"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\/978-3-031-93709-5_16","type":"book-chapter","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T09:50:10Z","timestamp":1754041810000},"page":"220-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Quantization of\u00a0Deep Neural Networks via\u00a0Layer Importance Estimation"],"prefix":"10.1007","author":[{"given":"Tushar","family":"Shinde","sequence":"first","affiliation":[]},{"given":"Sukanya","family":"Tukaram Naik","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,2]]},"reference":[{"issue":"7553","key":"16_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"issue":"3","key":"16_CR2","doi-asserted-by":"publisher","first-page":"60","DOI":"10.3390\/computers12030060","volume":"12","author":"Z Li","year":"2023","unstructured":"Li, Z., Li, H., Meng, L.: Model compression for deep neural networks: a survey. Computers 12(3), 60 (2023)","journal-title":"Computers"},{"doi-asserted-by":"crossref","unstructured":"Balaskas, K., et al.: Hardware-aware DNN compression via diverse pruning and mixed-precision quantization. IEEE Trans. Emerg. Top. Comput. (2024)","key":"16_CR3","DOI":"10.1109\/TETC.2023.3346944"},{"doi-asserted-by":"crossref","unstructured":"Guo, J., Xu, D., Ouyang, W.: Multidimensional pruning and its extension: a unified framework for model compression. IEEE Trans. Neural Netw. Learn. Syst. (2023)","key":"16_CR4","DOI":"10.1109\/TNNLS.2023.3266435"},{"unstructured":"Liu, Z., et al.: Rethinking the value of network pruning, arXiv preprint arXiv:1810.05270 (2018)","key":"16_CR5"},{"unstructured":"Li, H., et al.: Pruning filters for efficient convnets, arXiv preprint arXiv:1608.08710 (2016)","key":"16_CR6"},{"key":"16_CR7","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.neucom.2020.02.035","volume":"398","author":"S Swaminathan","year":"2020","unstructured":"Swaminathan, S., et al.: Sparse low rank factorization for deep neural network compression. Neurocomputing 398, 185\u2013196 (2020)","journal-title":"Neurocomputing"},{"doi-asserted-by":"crossref","unstructured":"Yin, M., et al.: Towards efficient tensor decomposition-based DNN model compression with optimization framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10674\u201310683 (2021)","key":"16_CR8","DOI":"10.1109\/CVPR46437.2021.01053"},{"unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network, arXiv preprint arXiv:1503.02531 (2015)","key":"16_CR9"},{"doi-asserted-by":"crossref","unstructured":"Sarfraz, F., Arani, E., Zonooz, B.: Knowledge distillation beyond model compression. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6136\u20136143. IEEE (2021)","key":"16_CR10","DOI":"10.1109\/ICPR48806.2021.9413016"},{"issue":"7","key":"16_CR11","doi-asserted-by":"publisher","first-page":"2925","DOI":"10.1109\/TNNLS.2020.3008996","volume":"32","author":"N Kim","year":"2020","unstructured":"Kim, N., et al.: Exploiting retraining-based mixed-precision quantization for low-cost DNN accelerator design. IEEE Trans. Neural Netw. Learn. Syst. 32(7), 2925\u20132938 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"16_CR12","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1109\/JPROC.2020.2976475","volume":"108","author":"L Deng","year":"2020","unstructured":"Deng, L., et al.: Model compression and hardware acceleration for neural networks: a comprehensive survey. Proc. IEEE 108(4), 485\u2013532 (2020)","journal-title":"Proc. IEEE"},{"key":"16_CR13","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. ON, Canada, Toronto (2009)"},{"issue":"6","key":"16_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3623402","volume":"14","author":"B Rokh","year":"2023","unstructured":"Rokh, B., Azarpeyvand, A., Khanteymoori, A.: A comprehensive survey on model quantization for deep neural networks in image classification. ACM Trans. Intell. Syst. Technol. 14(6), 1\u201350 (2023)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"12","key":"16_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3578938","volume":"55","author":"G Menghani","year":"2023","unstructured":"Menghani, G.: Efficient deep learning: a survey on making deep learning models smaller, faster, and better. ACM Comput. Surv. 55(12), 1\u201337 (2023)","journal-title":"ACM Comput. Surv."},{"issue":"10","key":"16_CR16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0292517","volume":"18","author":"G Yang","year":"2023","unstructured":"Yang, G., et al.: HMC: hybrid model compression method based on layer sensitivity grouping. PLoS ONE 18(10), e0292517 (2023)","journal-title":"PLoS ONE"},{"doi-asserted-by":"crossref","unstructured":"Koryakovskiy, I., et al.: One-shot model for mixed-precision quantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7939\u20137949 (2023)","key":"16_CR17","DOI":"10.1109\/CVPR52729.2023.00767"},{"doi-asserted-by":"crossref","unstructured":"Chen, W., Wang, P., Cheng, J.: Towards mixed-precision quantization of neural networks via constrained optimization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5350\u20135359 (2021)","key":"16_CR18","DOI":"10.1109\/ICCV48922.2021.00530"},{"doi-asserted-by":"crossref","unstructured":"Tang, C., et al.: Mixed-precision neural network quantization via learned layer-wise importance. In: European Conference on Computer Vision, pp. 259\u2013275. Springer (2022)","key":"16_CR19","DOI":"10.1007\/978-3-031-20083-0_16"},{"doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Layer importance estimation with imprinting for neural network quantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2408\u20132417 (2021)","key":"16_CR20","DOI":"10.1109\/CVPRW53098.2021.00273"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556 (2014)","key":"16_CR21"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"16_CR22","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Wang, K., et al.: 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)","key":"16_CR23","DOI":"10.1109\/CVPR.2019.00881"},{"unstructured":"McKinstry, J.L., et al.: Discovering low-precision networks close to full-precision networks for efficient embedded inference, arXiv preprint arXiv:1809.04191 (2018)","key":"16_CR24"},{"unstructured":"Hubara, I., et al.: Accurate post training quantization with small calibration sets. In: International Conference on Machine Learning, pp. 4466\u20134475. PMLR (2021)","key":"16_CR25"},{"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)","key":"16_CR26","DOI":"10.1109\/CVPR.2018.00286"},{"unstructured":"Hubara, I., et al.: Binarized neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)","key":"16_CR27"},{"doi-asserted-by":"crossref","unstructured":"Akkad, G., Mansour, A., Inaty, E.: Embedded deep learning accelerators: a survey on recent advances. IEEE Trans. Artif. Intell. (2023)","key":"16_CR28","DOI":"10.1109\/TAI.2023.3311776"},{"unstructured":"Choi, J., et al.: PACT: parameterized clipping activation for quantized neural networks, arXiv preprint arXiv:1805.06085 (2018)","key":"16_CR29"},{"doi-asserted-by":"crossref","unstructured":"Park, E., Yoo, S., Vajda, P.: Value-aware quantization for training and inference of neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 580\u2013595 (2018)","key":"16_CR30","DOI":"10.1007\/978-3-030-01225-0_36"},{"doi-asserted-by":"crossref","unstructured":"Elkerdawy, S., et al.: To filter prune, or to layer prune, that is the question. In: Proceedings of the Asian Conference on Computer Vision (2020)","key":"16_CR31","DOI":"10.1007\/978-3-030-69535-4_45"}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-93709-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T11:05:07Z","timestamp":1757329507000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-93709-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,2]]},"ISBN":["9783031937088","9783031937095"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-93709-5_16","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025,8,2]]},"assertion":[{"value":"2 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chennai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"20 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cvip2024.iiitdm.ac.in\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}