{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T14:10:32Z","timestamp":1743516632016,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031878961","type":"print"},{"value":"9783031878978","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\/978-3-031-87897-8_7","type":"book-chapter","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T13:34:39Z","timestamp":1743514479000},"page":"81-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KD-AHOSVD: Neural Network Compression via\u00a0Knowledge Distillation and\u00a0Tensor Decomposition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7384-1025","authenticated-orcid":false,"given":"Laura","family":"Meneghetti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-9543","authenticated-orcid":false,"given":"Edoardo","family":"Bianchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3107-9738","authenticated-orcid":false,"given":"Nicola","family":"Demo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0810-8812","authenticated-orcid":false,"given":"Gianluigi","family":"Rozza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"28684","DOI":"10.1109\/ACCESS.2021.3058103","volume":"9","author":"S Ahmadi-Asl","year":"2021","unstructured":"Ahmadi-Asl, S., et al.: Randomized algorithms for computation of tucker decomposition and Higher Order SVD (HOSVD). IEEE Access 9, 28684\u201328706 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3058103","journal-title":"IEEE Access"},{"key":"7_CR2","doi-asserted-by":"publisher","unstructured":"Bianchi, E., Lanz, O.: Egocentric video-based human action recognition in industrial environments. In: Concli, F., Maccioni, L., Vidoni, R., Matt, D.T. (eds.) Latest Advancements in Mechanical Engineering, pp. 257\u2013267. Springer Nature Switzerland, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70465-9_25","DOI":"10.1007\/978-3-031-70465-9_25"},{"key":"7_CR3","doi-asserted-by":"publisher","unstructured":"Brandoni, D., Simoncini, V.: Tensor-train decomposition for image recognition. Calcolo 57, 1\u201324 (2020). https:\/\/doi.org\/10.1007\/s10092-020-0358-8","DOI":"10.1007\/s10092-020-0358-8"},{"key":"7_CR4","doi-asserted-by":"publisher","unstructured":"Carroll, J.D., Chang, J.J.: Analysis of individual differences in multidimensional scaling via an N-way generalization of \u201cEckart-Young\u201d decomposition. Psychometrika 35(3), 283\u2013319 (1970). https:\/\/doi.org\/10.1007\/BF02310791","DOI":"10.1007\/BF02310791"},{"key":"7_CR5","doi-asserted-by":"publisher","unstructured":"Cichocki, A., Lee, N., Oseledets, I., Phan, A.H., Zhao, Q., Mandic, D.P., et\u00a0al.: Tensor networks for dimensionality reduction and large-scale optimization: Part 1 low-rank tensor decompositions. Foundations and Trends\u00ae in Machine Learning 9(4-5), 249\u2013429 (2016). https:\/\/doi.org\/10.1561\/2200000059","DOI":"10.1561\/2200000059"},{"issue":"4","key":"7_CR6","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1137\/19M1296070","volume":"2","author":"C Cui","year":"2020","unstructured":"Cui, C., Zhang, K., Daulbaev, T., Gusak, J., Oseledets, I., Zhang, Z.: Active subspace of neural networks: structural analysis and universal attacks. SIAM J. Math. Data Sci. 2(4), 1096\u20131122 (2020). https:\/\/doi.org\/10.1137\/19M1296070","journal-title":"SIAM J. Math. Data Sci."},{"issue":"4","key":"7_CR7","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1137\/S0895479896305696","volume":"21","author":"L De Lathauwer","year":"2000","unstructured":"De Lathauwer, L., De Moor, B., Vandewalle, J.: A multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21(4), 1253\u20131278 (2000). https:\/\/doi.org\/10.1137\/S0895479896305696","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"6","key":"7_CR8","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vision 129(6), 1789\u20131819 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01453-z","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR9","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, Conference Track Proceedings (2016)"},{"key":"7_CR10","unstructured":"Harshman, R.A.: Foundations of the PARAFAC procedure: models and conditions for an \u201cexplanatory\u201d multi-modal factor analysis. UCLA Working Pap. Phonetics 16, 1\u201384 (1970)"},{"key":"7_CR11","doi-asserted-by":"publisher","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1398\u20131406 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.155","DOI":"10.1109\/ICCV.2017.155"},{"key":"7_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network. In: NIPS Deep Learning and Representation Learning Workshop (2015)"},{"key":"7_CR13","unstructured":"Hugging Face: Optinum quanto: A PyTorch quantization backend for optimum. https:\/\/github.com\/huggingface\/optimum-quanto"},{"issue":"3","key":"7_CR14","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1137\/07070111X","volume":"51","author":"TG Kolda","year":"2009","unstructured":"Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455\u2013500 (2009). https:\/\/doi.org\/10.1137\/07070111X","journal-title":"SIAM Rev."},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Kumar, A., Shaikh, A.M., Li, Y., Bilal, H., Yin, B.: Pruning filters with l1-norm and capped l1-norm for CNN compression. Appl. Intell. 51, 1152\u20131160 (2021). https:\/\/doi.org\/10.1007\/s10489-020-01894-y","DOI":"10.1007\/s10489-020-01894-y"},{"key":"7_CR16","doi-asserted-by":"publisher","unstructured":"Li, Y., Adamczewski, K., Li, W., Gu, S., Timofte, R., Van\u00a0Gool, L.: Revisiting random channel pruning for neural network compression. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 191\u2013201 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00029","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Li, Y., Gu, S., Van\u00a0Gool, L., Timofte, R.: Learning filter basis for convolutional neural network compression. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5622\u20135631 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00572","DOI":"10.1109\/ICCV.2019.00572"},{"issue":"2","key":"7_CR18","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MCAS.2023.3267921","volume":"23","author":"X Liu","year":"2023","unstructured":"Liu, X., Parhi, K.K.: Tensor decomposition for model reduction in neural networks: a review [feature]. IEEE Circuits Syst. Mag. 23(2), 8\u201328 (2023). https:\/\/doi.org\/10.1109\/MCAS.2023.3267921","journal-title":"IEEE Circuits Syst. Mag."},{"key":"7_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/C2020-0-01790-1","author":"Y Liu","year":"2021","unstructured":"Liu, Y.: Tensors for data processing: theory, methods, and applications. Acad. Press (2021). https:\/\/doi.org\/10.1016\/C2020-0-01790-1","journal-title":"Acad. Press"},{"key":"7_CR20","doi-asserted-by":"publisher","unstructured":"Meneghetti, L., Demo, N., Rozza, G.: A proper orthogonal decomposition approach for parameters reduction of single shot detector networks. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 2206\u20132210 (2022). https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897513","DOI":"10.1109\/ICIP46576.2022.9897513"},{"key":"7_CR21","doi-asserted-by":"publisher","unstructured":"Meneghetti, L., Demo, N., Rozza, G.: A dimensionality reduction approach for convolutional neural networks. Appl. Intell. 1\u201316 (2023). https:\/\/doi.org\/10.1007\/s10489-023-04730-1","DOI":"10.1007\/s10489-023-04730-1"},{"issue":"12","key":"7_CR22","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). https:\/\/doi.org\/10.1145\/3578938","journal-title":"ACM Comput. Surv."},{"key":"7_CR23","doi-asserted-by":"publisher","unstructured":"Messaoud, S., Bouaafia, S., Maraoui, A., Ammari, A.C., Khriji, L., Machhout, M.: Deep convolutional neural networks-based hardware\u2013software on-chip system for computer vision application. Comput. Electr. Eng. 98, 107671 (2022). https:\/\/doi.org\/10.1016\/j.compeleceng.2021.107671","DOI":"10.1016\/j.compeleceng.2021.107671"},{"issue":"5","key":"7_CR24","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets, I.V.: Tensor-train decomposition. SIAM J. Sci. Comput. 33(5), 2295\u20132317 (2011). https:\/\/doi.org\/10.1137\/090752286","journal-title":"SIAM J. Sci. Comput."},{"issue":"5","key":"7_CR25","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1109\/JPROC.2021.3074329","volume":"109","author":"Y Panagakis","year":"2021","unstructured":"Panagakis, Y., et al.: Tensor methods in computer vision and deep learning. Proc. IEEE 109(5), 863\u2013890 (2021). https:\/\/doi.org\/10.1109\/JPROC.2021.3074329","journal-title":"Proc. IEEE"},{"key":"7_CR26","volume-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","author":"A Paszke","year":"2019","unstructured":"Paszke, A., et al.: PyTorch: An Imperative Style, High-Performance Deep Learning Library. Curran Associates Inc., Red Hook, NY, USA (2019)"},{"key":"7_CR27","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"HE Robbins","year":"1951","unstructured":"Robbins, H.E.: A stochastic approximation method. Ann. Math. Stat. 22, 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"7_CR28","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR (2015)"},{"key":"7_CR29","unstructured":"Tucker, L.R.: The extension of factor analysis to three-dimensional matrices. In: Gulliksen, H., Frederiksen, N. (eds.) Contributions to Mathematical Psychology., pp. 110\u2013127. Holt, Rinehart and Winston, New York (1964)"},{"issue":"3","key":"7_CR30","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF02289464","volume":"31","author":"LR Tucker","year":"1966","unstructured":"Tucker, L.R.: Some mathematical notes on three-mode factor analysis. Psychometrika 31(3), 279\u2013311 (1966). https:\/\/doi.org\/10.1007\/BF02289464","journal-title":"Psychometrika"},{"key":"7_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2020.103094","volume":"76","author":"R Udendhran","year":"2020","unstructured":"Udendhran, R., Balamurugan, M., Suresh, A., Varatharajan, R.: Enhancing image processing architecture using deep learning for embedded vision systems. Microprocess. Microsyst. 76, 103094 (2020). https:\/\/doi.org\/10.1016\/j.micpro.2020.103094","journal-title":"Microprocess. Microsyst."},{"key":"7_CR32","unstructured":"Yang, J., Martinez, B., Bulat, A., Tzimiropoulos, G.: Knowledge distillation via softmax regression representation learning. In: International Conference on Learning Representations (2021)"},{"key":"7_CR33","doi-asserted-by":"publisher","unstructured":"Yang, J., et al.: Quantization networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7300\u20137308 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00748","DOI":"10.1109\/CVPR.2019.00748"}],"container-title":["Lecture Notes in Computer Science","Design and Architecture for Signal and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-87897-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T13:35:10Z","timestamp":1743514510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-87897-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031878961","9783031878978"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-87897-8_7","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":"1 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"DASIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Design and Architectures for Signal and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Barcelona","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 January 2025","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":"dasip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasipws.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}