{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T21:07:12Z","timestamp":1762376832980,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2020AAA0105600","2019YFB1312000"],"award-info":[{"award-number":["2020AAA0105600","2019YFB1312000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076195","62006183"],"award-info":[{"award-number":["62076195","62006183"]}],"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":[[2021,10]]},"DOI":"10.1109\/tnnls.2020.3017692","type":"journal-article","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T20:26:45Z","timestamp":1605904005000},"page":"4404-4418","source":"Crossref","is-referenced-by-count":3,"title":["Analogy-Detail Networks for Object Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3328-5412","authenticated-orcid":false,"given":"Xiaoyu","family":"Tao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0611-0636","authenticated-orcid":false,"given":"Xiaopeng","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8820-8970","authenticated-orcid":false,"given":"Weiwei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyuan","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1793-5836","authenticated-orcid":false,"given":"Yihong","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/089892903321662976"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012375731-9\/50029-X"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.05.005"},{"key":"ref4","first-page":"2956","article-title":"Look and think twice: Capturing top-down visual attention with feedback","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Cao"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.09.031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref7","article-title":"Attention to scale: Scale-aware semantic image segmentation","volume-title":"arXiv:1511.03339","author":"Chen","year":"2015"},{"key":"ref8","article-title":"Deeply-supervised nets","volume-title":"arXiv:1409.5185","author":"Lee","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-6123(06)55001-0"},{"key":"ref13","article-title":"Shake-shake regularization","volume-title":"arXiv:1705.07485","author":"Gastaldi","year":"2017"},{"key":"ref14","first-page":"1","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Geirhos"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2892035"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"630","article-title":"Identity mappings in deep residual networks","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"He"},{"key":"ref21","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","volume-title":"arXiv:1704.04861","author":"Howard","year":"2017"},{"key":"ref22","first-page":"1457","article-title":"Non-negative matrix factorization with sparseness constraints","volume":"5","author":"Hoyer","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","article-title":"Squeeze-and-excitation networks","volume-title":"arXiv:1709.01507","author":"Hu","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref25","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"arXiv:1502.03167","author":"Ioffe","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2017.2689098"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"issue":"19","key":"ref30","first-page":"109","article-title":"Inferotemporal cortex and object vision","volume":"19","author":"Kuppens","year":"1996","journal-title":"Annu. Rev. Neurosci."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref34","first-page":"1","article-title":"Network in network","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lin"},{"key":"ref35","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS)","author":"Netzer"},{"key":"ref36","article-title":"You only look once: Unified, real-time object detection","volume-title":"arXiv:1506.02640","author":"Redmon","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref39","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref40","first-page":"1","article-title":"Training very deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Srivastava"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref43","article-title":"Rethinking the inception architecture for computer vision","volume-title":"arXiv:1512.00567","author":"Szegedy","year":"2015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6060"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"issue":"7","key":"ref48","first-page":"2872","article-title":"Improving CNN performance accuracies with min-max objective","volume":"29","author":"Shi","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref49","first-page":"1","article-title":"Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wieland"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref51","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","volume-title":"arXiv:1511.05234","author":"Xu","year":"2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.305"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref55","article-title":"Neural architecture search with reinforcement learning","volume-title":"arXiv:1611.01578","author":"Zoph","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9559436\/09265452.pdf?arnumber=9265452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:05:43Z","timestamp":1706058343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9265452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":56,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3017692","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}