{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:53:03Z","timestamp":1777128783811,"version":"3.51.4"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62133012"],"award-info":[{"award-number":["62133012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936006"],"award-info":[{"award-number":["61936006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073255"],"award-info":[{"award-number":["62073255"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303366"],"award-info":[{"award-number":["62303366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Capability Support Program of Shaanxi","award":["2021TD-05"],"award-info":[{"award-number":["2021TD-05"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["QTZX24072"],"award-info":[{"award-number":["QTZX24072"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["QTZX23039"],"award-info":[{"award-number":["QTZX23039"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["XJSJ23030"],"award-info":[{"award-number":["XJSJ23030"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tnnls.2024.3439435","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T13:44:31Z","timestamp":1725025471000},"page":"8540-8553","source":"Crossref","is-referenced-by-count":3,"title":["SAAF: Self-Adaptive Attention Factor-Based Taylor-Pruning on Convolutional Neural Networks"],"prefix":"10.1109","volume":"36","author":[{"given":"Yiheng","family":"Lu","sequence":"first","affiliation":[{"name":"Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0415-8556","authenticated-orcid":false,"given":"Maoguo","family":"Gong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4970-4175","authenticated-orcid":false,"given":"Kaiyuan","family":"Feng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University, Xi’an, China"}]},{"given":"Jialu","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2413-4698","authenticated-orcid":false,"given":"Ziyu","family":"Guan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6294-6761","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3066241"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3043444"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068749"},{"key":"ref10","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref11","first-page":"263","article-title":"Optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hassibi"},{"key":"ref12","first-page":"1","article-title":"Pruning filters for efficient ConvNets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref14","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016","journal-title":"arXiv:1611.06440"},{"key":"ref15","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.31"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref18","first-page":"1","article-title":"Variational dropout sparsifies deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Molchanov"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2946636"},{"key":"ref20","first-page":"1","article-title":"Learning sparse neural networks through L0 regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Louizos"},{"key":"ref21","first-page":"1","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jonathan"},{"key":"ref22","article-title":"Layer-compensated pruning for resource-constrained convolutional neural networks","author":"Chin","year":"2018","journal-title":"arXiv:1810.00518"},{"key":"ref23","article-title":"Filter distillation for network compression","author":"Suau","year":"2018","journal-title":"arXiv:1807.10585"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/318"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref27","first-page":"1","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ye"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref29","first-page":"1","article-title":"Runtime neural pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00447"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3066410"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00915"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR49039.2020.00040"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref37","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Romero"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref39","first-page":"1","article-title":"Constrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tian"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01603"},{"key":"ref41","first-page":"3438","article-title":"Bayesian dark knowledge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Korattikara"},{"key":"ref42","article-title":"Knowledge distillation beyond model compression","author":"Sarfraz","year":"2020","journal-title":"arXiv:2007.01922"},{"key":"ref43","article-title":"InDistill: Information flow-preserving knowledge distillation for model compression","author":"Sarridis","year":"2022","journal-title":"arXiv:2205.10003"},{"key":"ref44","first-page":"1","article-title":"Compressing neural networks with the hashing trick","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3279281"},{"key":"ref48","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1","author":"Courbariaux","year":"2016","journal-title":"arXiv:1602.02830"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_37"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00638"},{"key":"ref52","first-page":"17737","article-title":"Post-training sparsity-aware quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Shomron"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"ref55","first-page":"3822","article-title":"Breaking the curse of space explosion: Towards efficient nas with curriculum search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00938"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.09.002"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3086914"},{"key":"ref59","first-page":"1","article-title":"Rethinking the pruning criteria for convolutional neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3035028"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084856"},{"key":"ref62","first-page":"1607","article-title":"Approximated Oracle filter pruning for destructive CNN width optimization","volume-title":"Proc. Int. Conf. Mach. Learn. Represent.","author":"Ding"},{"key":"ref63","first-page":"14747","article-title":"Storage efficient and dynamic flexible runtime channel pruning via deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069970"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3097938"},{"key":"ref67","article-title":"Convolution neural network architecture learning for remote sensing scene classification","author":"Chen","year":"2020","journal-title":"arXiv:2001.09614"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3277077"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.11.025"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3001401"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10982361\/10659741.pdf?arnumber=10659741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:47:14Z","timestamp":1765997234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10659741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":72,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3439435","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}