{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:23:04Z","timestamp":1740169384755,"version":"3.37.3"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"U.S. DEVCOM Army Research Laboratory through Booz Allen Hamilton","award":["W911QX-21-D-0001"],"award-info":[{"award-number":["W911QX-21-D-0001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3485557","type":"journal-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T17:50:05Z","timestamp":1729705805000},"page":"174222-174244","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing GANs With MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0486-0756","authenticated-orcid":false,"given":"Prasanna","family":"Reddy Pulakurthi","sequence":"first","affiliation":[{"name":"Rochester Institute of Technology, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5898-8224","authenticated-orcid":false,"given":"Mahsa","family":"Mozaffari","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, NY, USA"}]},{"given":"Sohail A.","family":"Dianat","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6860-0844","authenticated-orcid":false,"given":"Jamison","family":"Heard","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6481-4175","authenticated-orcid":false,"given":"Raghuveer M.","family":"Rao","sequence":"additional","affiliation":[{"name":"U.S. DEVCOM Army Research Laboratory, Adelphi, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6289-0500","authenticated-orcid":false,"given":"Majid","family":"Rabbani","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3440207"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130191"},{"key":"ref3","first-page":"21357","article-title":"ContraGAN: Contrastive learning for conditional image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023153"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101552"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref10","article-title":"Garment design with generative adversarial networks","volume-title":"arXiv:2007.10947","author":"Yuan","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3171433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3864965"},{"key":"ref13","first-page":"1","article-title":"MMD GAN: Towards deeper understanding of moment matching network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Li"},{"key":"ref14","article-title":"Improving MMD-GAN training with repulsive loss function","volume-title":"arXiv:1812.09916","author":"Wang","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00572"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.08681"},{"key":"ref17","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref18","first-page":"1","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref19","article-title":"Input perturbation reduces exposure bias in diffusion models","volume-title":"arXiv:2301.11706","author":"Ning","year":"2023"},{"key":"ref20","article-title":"Diffusion-GAN: Training GANs with diffusion","volume-title":"arXiv:2206.02262","author":"Wang","year":"2022"},{"key":"ref21","first-page":"32270","article-title":"Maximum likelihood training of implicit nonlinear diffusion model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kim"},{"key":"ref22","article-title":"Soft diffusion: Score matching for general corruptions","volume-title":"arXiv:2209.05442","author":"Daras","year":"2022"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446488"},{"key":"ref25","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref26","first-page":"1","article-title":"Hierarchical implicit models and likelihood-free variational inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tran"},{"key":"ref27","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref28","first-page":"1","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gulrajani"},{"key":"ref29","article-title":"Demystifying MMD GANs","volume-title":"arXiv:1801.01401","author":"Bi\u0142kowski","year":"2018"},{"key":"ref30","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"arXiv:1511.06434","author":"Radford","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00332"},{"key":"ref33","article-title":"AGAN: Towards automated design of generative adversarial networks","volume-title":"arXiv:1906.11080","author":"Wang","year":"2019"},{"key":"ref34","article-title":"DARTS: Differentiable architecture search","volume-title":"arXiv:1806.09055","author":"Liu","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref36","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Maas"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1710.05941"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01198"},{"key":"ref40","first-page":"28560","article-title":"Revisiting discriminator in GAN compression: A generator-discriminator cooperative compression scheme","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00672"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01949"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16980"},{"key":"ref44","article-title":"GANs can play lottery tickets too","volume-title":"arXiv:2106.00134","author":"Chen","year":"2021"},{"key":"ref45","first-page":"1","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"LeCun"},{"key":"ref46","first-page":"1","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"5","author":"Hassibi"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_4"},{"key":"ref48","first-page":"1","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han"},{"key":"ref49","first-page":"1","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Wen"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00333"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01214"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00533"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_31"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01053"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3038227"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.09.006"},{"key":"ref59","first-page":"1","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Denton"},{"key":"ref60","first-page":"1","article-title":"Predicting parameters in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Denil"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489213"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00306"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1137\/090748330"},{"key":"ref64","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","volume-title":"arXiv:1511.06530","author":"Kim","year":"2015"},{"issue":"1","key":"ref65","first-page":"1","article-title":"Global analytic solution of fully-observed variational Bayesian matrix factorization","volume":"14","author":"Nakajima","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"ref67","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. AISTATS","author":"Glorot"},{"key":"ref68","first-page":"1","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Li"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref71","article-title":"Spectral normalization for generative adversarial networks","volume-title":"arXiv:1802.05957","author":"Miyato","year":"2018"},{"key":"ref72","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"arXiv:1710.10196","author":"Karras","year":"2017"},{"key":"ref73","first-page":"7559","article-title":"Differentiable augmentation for data-efficient gan training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhao"},{"key":"ref74","first-page":"14745","article-title":"TransGAN: Two pure transformers can make one strong GAN, and that can scale up","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Jiang"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref75"},{"key":"ref76","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Coates"},{"key":"ref77","article-title":"Deep learning face attributes in the wild","volume-title":"arXiv:1411.7766","author":"Liu","year":"2014"},{"key":"ref78","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2017"},{"key":"ref79","article-title":"TensorLy: Tensor learning in Python","volume-title":"arXiv:1610.09555","author":"Kossaifi","year":"2016"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01243"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00475"},{"key":"ref82","article-title":"CGANs with projection discriminator","volume-title":"arXiv:1802.05637","author":"Miyato","year":"2018"},{"key":"ref83","first-page":"1","article-title":"Twin auxilary classifiers GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Gong"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00754"},{"key":"ref85","first-page":"480","article-title":"A contrastive learning approach for training variational autoencoder priors","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Aneja"},{"key":"ref86","first-page":"3367","article-title":"Optimal budgeted rejection sampling for generative models","volume-title":"Proc. 27th Int. Conf. Artif. Intell. Statist.","volume":"238","author":"Verine"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3051488"},{"key":"ref88","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.109856","article-title":"Compressing convolutional neural networks with hierarchical Tucker-2 decomposition","volume":"132","author":"Gabor","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref89","article-title":"Tensor ring decomposition","volume-title":"arXiv:1606.05535","author":"Zhao","year":"2016"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3370294"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10732016.pdf?arnumber=10732016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T05:40:27Z","timestamp":1732772427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10732016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3485557","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}