{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T04:21:22Z","timestamp":1743826882046,"version":"3.40.3"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"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":["62276123","61921006","61772256"],"award-info":[{"award-number":["62276123","61921006","61772256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tpami.2023.3329498","type":"journal-article","created":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T17:53:46Z","timestamp":1698947626000},"page":"1290-1304","source":"Crossref","is-referenced-by-count":0,"title":["Tobias: A Random CNN Sees Objects"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6229-8469","authenticated-orcid":false,"given":"Yun-Hao","family":"Cao","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2085-7568","authenticated-orcid":false,"given":"Jianxin","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/3-540-46805-6_19","article-title":"Object recognition with gradient-based learning","volume":"1681","author":"Forsyth","year":"1999","journal-title":"Shape Contour Grouping Comput. Vis."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref3","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref5","first-page":"1","article-title":"Inductive bias of deep convolutional networks through pooling geometry","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cohen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01347"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref15","first-page":"21271","article-title":"Boostrap your own latent: A new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grill"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19894"},{"key":"ref17","first-page":"1","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01604"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00082"},{"key":"ref20","first-page":"6682","article-title":"Proving the lottery ticket hypothesis: Pruning is all you need","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Malach"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01303-4"},{"key":"ref22","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. Representations","author":"Geirhos"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.698"},{"key":"ref24","first-page":"204","article-title":"DeepUSPS: Deep robust unsupervised saliency prediction via self-supervision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00766"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20119"},{"article-title":"Beyond single instance multi-view unsupervised representation learning","year":"2020","author":"Chu","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.146"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref35","first-page":"4905","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1973.4309314"},{"article-title":"The CalTech-UCSD Birds-200\u20132011 dataset","year":"2011","author":"Wah","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704472"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref42","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.360"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.70"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref51","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref52"},{"article-title":"Improved baselines with momentum contrastive learning","year":"2020","author":"Chen","key":"ref53"},{"article-title":"Rethinking self-supervised learning: Small is beautiful","year":"2021","author":"Cao","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"article-title":"Detectron2","year":"2019","author":"Wu","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref62","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10384454\/10305409.pdf?arnumber=10305409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:31:11Z","timestamp":1743795071000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10305409\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3329498","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}