{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:00:28Z","timestamp":1770224428339,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","funder":[{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"publisher","award":["SRG\/2019\/001938"],"award-info":[{"award-number":["SRG\/2019\/001938"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006593","name":"Board of Research in Nuclear Sciences","doi-asserted-by":"publisher","award":["59\/20\/11\/2020-BRNS"],"award-info":[{"award-number":["59\/20\/11\/2020-BRNS"]}],"id":[{"id":"10.13039\/501100006593","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":[[2021]]},"DOI":"10.1109\/tpami.2021.3112816","type":"journal-article","created":{"date-parts":[[2021,9,16]],"date-time":"2021-09-16T20:34:21Z","timestamp":1631824461000},"page":"1-1","source":"Crossref","is-referenced-by-count":6,"title":["Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Data"],"prefix":"10.1109","author":[{"given":"Gaurav Kumar","family":"Nayak","sequence":"first","affiliation":[]},{"given":"Konda Reddy","family":"Mopuri","sequence":"additional","affiliation":[]},{"given":"Saksham","family":"Jain","sequence":"additional","affiliation":[]},{"given":"Anirban","family":"Chakraborty","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","article-title":"Learning multiple layers of features from tiny images","volume-title":"Tech. Rep.","author":"Krizhevsky","year":"2009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_2"},{"key":"ref6","first-page":"8317","article-title":"Zero-shot knowledge distillation in deep networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Nayak"},{"key":"ref7","first-page":"1","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"Proc. Int. Conf. Learn. Representations Workshops","author":"Simonyan"},{"key":"ref8","article-title":"Striving for simplicity: The all convolutional net","volume-title":"Proc. Int. Conf. Learn. Representations Workshops","author":"Springenberg"},{"key":"ref9","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref11","first-page":"1","article-title":"Data-free knowledge distillation for deep neural networks","volume-title":"Proc. LLD Workshop Neural Inf. Process. Syst.","author":"Lopes"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref13","first-page":"9551","article-title":"Zero-shot knowledge transfer via adversarial belief matching","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Micaelli"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5709"},{"key":"ref15","first-page":"2705","article-title":"Knowledge extraction with no observable data","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Yoo"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00852"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"ref21","first-page":"2994","article-title":"Continual learning with deep generative replay","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093365"},{"key":"ref24","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref26","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"Tzeng","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00460"},{"key":"ref30","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00066"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref33","first-page":"1","article-title":"Fast feature fool: A data independent approach to universal adversarial perturbations","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Mopuri"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2861800"},{"key":"ref35","article-title":"Inceptionism: Going deeper into neural networks","author":"Mordvintsev","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/0471722227"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/0471722227.ch27"},{"key":"ref38","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref40","first-page":"1097","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe"},{"key":"ref41","article-title":"A kernel theory of modern data augmentation","author":"Dao","year":"2018"},{"key":"ref42","article-title":"Few-shot learning of neural networks from scratch by pseudo example optimization","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Kimura"},{"key":"ref43","first-page":"1","article-title":"Feature visualization","author":"Olah","year":"2017"},{"key":"ref44","article-title":"Google deep dream","author":"Mordvintsev","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref46","first-page":"1","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref47","article-title":"Adversarial machine learning at scale","author":"Kurakin","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00283"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref50","article-title":"Fast and accurate digit classification","volume-title":"Tech. Rep. UCB\/EECS-2009\u2013159","author":"Maji","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.274"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.316","article-title":"Adversarial discriminative domain adaptation","author":"Tzeng","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref55","article-title":"Coupled generative adversarial networks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref56","first-page":"469","article-title":"Three scenarios for continual learning","author":"van de Ven","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09540299.pdf?arnumber=9540299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:12:34Z","timestamp":1705014754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9540299\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3112816","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}