{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T21:51:50Z","timestamp":1771537910556,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong RGC GRF Project","award":["PolyU 152135\/16E"],"award-info":[{"award-number":["PolyU 152135\/16E"]}]},{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"publisher","award":["61971086"],"award-info":[{"award-number":["61971086"]}],"id":[{"id":"10.13039\/501100001809","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":[[2022,8]]},"DOI":"10.1109\/tnnls.2021.3052829","type":"journal-article","created":{"date-parts":[[2021,2,2]],"date-time":"2021-02-02T04:26:13Z","timestamp":1612239973000},"page":"3400-3414","source":"Crossref","is-referenced-by-count":2,"title":["Detachable Second-Order Pooling: Toward High-Performance First-Order Networks"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9386-194X","authenticated-orcid":false,"given":"Lida","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong"}]},{"given":"Jiangtao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7229-3867","authenticated-orcid":false,"given":"Peihua","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2078-4215","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. NeurIPS","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref4","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","author":"Huang","year":"2007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.527"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2872675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.149"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.103"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2861991"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522428"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.689"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.228"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref22","first-page":"1","article-title":"Network in network","volume-title":"Proc. ICLR","author":"Lin"},{"key":"ref23","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv:1503.02531"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.63"},{"key":"ref27","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref29","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref31","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. ICML","author":"Ioffe"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.339"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref35","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. ICML","author":"Furlanello"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/050637996"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.229"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.152"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref42","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref45","first-page":"1","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. ICML","author":"Sutskever"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref47","first-page":"1","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","volume-title":"Proc. ICLR","author":"Mishra"},{"key":"ref48","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Prof. ICML","author":"Tan"},{"key":"ref49","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017","journal-title":"arXiv:1710.05941"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17275"},{"key":"ref51","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref52","article-title":"Improving generalization performance by switching from adam to SGD","author":"Shirish Keskar","year":"2017","journal-title":"arXiv:1712.07628"},{"key":"ref53","first-page":"1","article-title":"Adaptive gradient methods with dynamic bound of learning rate","volume-title":"Proc. ICLR","author":"Luo"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9849214\/09343714.pdf?arnumber=9343714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:22:57Z","timestamp":1704846177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9343714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":53,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3052829","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8]]}}}