{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:15:12Z","timestamp":1766733312542,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI Grant-in-Aid for Scientific Research on Innovative Areas","doi-asserted-by":"publisher","award":["JP19H04982"],"award-info":[{"award-number":["JP19H04982"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Grant-in-Aid for Scientific Research","award":["JP18H04106"],"award-info":[{"award-number":["JP18H04106"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3186101","type":"journal-article","created":{"date-parts":[[2022,6,24]],"date-time":"2022-06-24T19:36:17Z","timestamp":1656099377000},"page":"68384-68396","source":"Crossref","is-referenced-by-count":7,"title":["Knowledge Transferred Fine-Tuning: Convolutional Neural Network Is Born Again With Anti-Aliasing Even in Data-Limited Situations"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1423-3767","authenticated-orcid":false,"given":"Satoshi","family":"Suzuki","sequence":"first","affiliation":[{"name":"NTT Computer and Data Science Laboratories, NTT Corporation, Yokosuka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7138-4983","authenticated-orcid":false,"given":"Shoichiro","family":"Takeda","sequence":"additional","affiliation":[{"name":"NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Makishima","sequence":"additional","affiliation":[{"name":"NTT Computer and Data Science Laboratories, NTT Corporation, Yokosuka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3971-0654","authenticated-orcid":false,"given":"Atsushi","family":"Ando","sequence":"additional","affiliation":[{"name":"NTT Computer and Data Science Laboratories, NTT Corporation, Yokosuka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Masumura","sequence":"additional","affiliation":[{"name":"NTT Computer and Data Science Laboratories, NTT Corporation, Yokosuka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2412-0184","authenticated-orcid":false,"given":"Hayaru","family":"Shouno","sequence":"additional","affiliation":[{"name":"Department of Informatics, The University of Electro-Communications, Chofu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00342633"},{"key":"ref4","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky"},{"key":"ref5","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","first-page":"7324","article-title":"Making convolutional networks shift-invariant again","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/T-AIEE.1928.5055024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00727"},{"key":"ref10","first-page":"21653","article-title":"Curriculum by smoothing","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sinha"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01672-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2500224"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00494"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506696"},{"key":"ref17","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Represent. Learn. Workshop","author":"Hinton"},{"key":"ref18","first-page":"1","article-title":"Few-shot learning of neural networks from scratch by pseudo example optimization","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Kimura"},{"key":"ref19","first-page":"1","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Furlanello"},{"key":"ref20","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Romero"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Caltech-256 object category dataset","year":"2007","author":"Griffin","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92307-5_84"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref27","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Goodfellow"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref29","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Szegedy"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref31","first-page":"1","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ba"},{"key":"ref32","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zagoruyko"},{"key":"ref33","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"Huang","year":"2017","journal-title":"arXiv:1707.01219"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref37","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv:1312.4400"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7566-5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01428"},{"key":"ref40","first-page":"1","article-title":"Adversarial examples are not bugs, they are features","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ilyas"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref42","first-page":"1","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref44","first-page":"1","article-title":"Multi-task learning as multi-objective optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sener"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref46","first-page":"1","article-title":"Empirical evaluation of rectified activations in convolutional network","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML) Deep Learn. Workshop","author":"Xu"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09805722.pdf?arnumber=9805722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:21:42Z","timestamp":1706761302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9805722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3186101","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}