{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:02:58Z","timestamp":1782482578928,"version":"3.54.5"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tai.2023.3323918","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T13:55:26Z","timestamp":1697118926000},"page":"2638-2650","source":"Crossref","is-referenced-by-count":12,"title":["Kullback\u2013Leibler Divergence-Based Regularized Normalization for Low-Resource Tasks"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0485-392X","authenticated-orcid":false,"given":"Neeraj","family":"Kumar","sequence":"first","affiliation":[{"name":"Bharti School of Telecommunication Technology & Management, Indian Institute of Technology Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Narang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-3071","authenticated-orcid":false,"given":"Brejesh","family":"Lall","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref2","article-title":"Layer\n      normalization","author":"Ba","year":"2016"},{"key":"ref3","article-title":"Instance\n      normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref7","article-title":"Language\n      models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref8","article-title":"wav2vec 2.0: A\n      framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref9","article-title":"End-to-end\n      whisper to natural speech conversion using modified transformer\n     network","author":"Niranjan","year":"2021"},{"key":"ref10","first-page":"1571","article-title":"Bilinear\n      attention networks","volume-title":"Proc. 32th Int. Adv. Conf. Neural Inf.\n      Process. Syst.","author":"Kim","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref12","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref13","first-page":"2563","article-title":"Batch-instance\n      normalization for adaptively style-invariant neural networks","volume-title":"Proc. 32nd Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Nam","year":"2018"},{"key":"ref14","article-title":"Recurrent\n      batch normalization","volume-title":"Proc. 5th Int. Conf. Learn.\n      Representations","author":"Cooijmans","year":"2017"},{"key":"ref15","first-page":"901","article-title":"Weight\n      normalization: A simple reparameterization to accelerate training of deep neural\n      networks","volume-title":"Proc. 30th Int. Adv. Conf. Neural Inf. Process.\n      Syst.","author":"Salimans","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-556"},{"key":"ref18","first-page":"16304","article-title":"Stochastic\n      normalization","volume-title":"Proc. 34th Int. Adv. Conf. Neural Inf.\n      Process. Syst.","author":"Kou","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2932062"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034828"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2007.05.028"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1163"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"issue":"1","key":"ref24","first-page":"2096","article-title":"Domain-adversarial training of neural\n     networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab39d9"},{"key":"ref26","first-page":"876","article-title":"Averaging\n      weights leads to wider optima and better generalization","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Izmailov","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1424"},{"key":"ref28","article-title":"Deep speech: Scaling up end-to-end speech\n      recognition","author":"Hannun","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10873"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1280"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00500"},{"key":"ref33","article-title":"Auto-encoding\n      variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn.\n      Representations","author":"Kingma","year":"2014"},{"key":"ref34","article-title":"Beta-VAE: Learning basic visual concepts with a constrained\n      variational framework","volume-title":"Proc. Int. Conf. Learn.\n      Representations","author":"Higgins","year":"2016"},{"key":"ref35","article-title":"Deep\n      variational information bottleneck","volume-title":"Proc. 5th Int. Conf.\n      Learn. Representations","author":"Alemi","year":"2017"},{"key":"ref36","article-title":"Distilling the\n      knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn.\n      Representation Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref37","first-page":"141","article-title":"Towards\n      feature distribution alignment and diversity enhancement for data-free\n      quantization","volume-title":"Proc. IEEE Int. Conf. Data\n      Mining","author":"Chaitanya","year":"2022"},{"key":"ref38","first-page":"121","article-title":"Dictionary\n      pair-based data-free fast deep neural network compression","volume-title":"Proc. IEEE Int. Conf. Data Mining","author":"Gao","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.07.042"},{"key":"ref40","article-title":"Semi-supervised\n      anomaly detection algorithm based on KL divergence (SAD-KL)","volume-title":"Proc. Defense + Commercial Sens.","author":"Lee","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106093"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6355"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCP54855.2022.9887763"},{"key":"ref44","article-title":"Robust phase retrieval via reverse Kullback-Leibler divergence and\n      Wirtinger flow","author":"Choudhury","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107983"},{"issue":"1","key":"ref46","first-page":"1929","article-title":"Dropout:\n      A simple way to prevent neural networks from overfitting","volume":"1","author":"Srivastava","year":"2014","journal-title":"J.\n      Mach. Learn. Res."},{"key":"ref47","article-title":"Mixout: Effective\n      regularization to finetune large-scale pretrained language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2019"},{"key":"ref48","first-page":"950","article-title":"A simple weight\n      decay can improve generalization","volume-title":"Proc. 4th Int. Adv. Conf.\n      Neural Inf. Process. Syst.","author":"Krogh","year":"1992"},{"key":"ref49","article-title":"Learning\n      confidence for out-of-distribution detection in neural networks","author":"Devries","year":"2018"},{"key":"ref50","article-title":"Novelty\n      detection with GAN","author":"Kliger","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref53","article-title":"Revisiting\n      few-sample BERT fine-tuning","volume-title":"Proc. Int. Conf. Learn.\n      Representations","author":"Zhang","year":"2021"},{"key":"ref54","article-title":"On the\n      stability of fine-tuning BERT: Misconceptions, explanations, and strong\n      baselines","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mosbach","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.769"},{"key":"ref56","first-page":"216","article-title":"A SICK cure\n      for the evaluation of compositional distributional semantic models","volume-title":"Proc. 9th Int. Conf. Lang. Resour. Eval.","author":"Marelli","year":"2014"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1204"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00068"},{"key":"ref59","first-page":"100","article-title":"Natural\n      language inference from multiple premises","volume-title":"Proc. 8th Int.\n      Joint Conf. Natural Lang. Process.","author":"Lai","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12022"},{"key":"ref61","first-page":"996","article-title":"Inference is\n      everything: Recasting semantic resources into a unified evaluation\n     framework","volume-title":"Proc. 8th Int. Joint Conf. Natural Lang.\n      Process.","author":"White","year":"2017"},{"key":"ref62","first-page":"777","article-title":"Resolving complex\n      cases of definite pronouns: The Winograd Schema Challenge","volume-title":"Proc. Joint Conf. Empirical Methods Natural Lang. Process. Computat. Natural Lang.\n      Learn.","author":"Rahman","year":"2012"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2067"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00152"},{"key":"ref65","article-title":"Natural language\n      inference over interaction space","volume-title":"Proc. Int. Conf. Learn.\n      Representations","author":"Gong","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/579"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1002"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S19-1028"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2017"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10571778\/10283903.pdf?arnumber=10283903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:01Z","timestamp":1755911341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10283903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":69,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tai.2023.3323918","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}