{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:34:47Z","timestamp":1781714087350,"version":"3.54.5"},"reference-count":28,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,9,1]]},"DOI":"10.1587\/transinf.2022edp7019","type":"journal-article","created":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T22:23:02Z","timestamp":1661984582000},"page":"1537-1545","source":"Crossref","is-referenced-by-count":3,"title":["Improving Noised Gradient Penalty with Synchronized Activation Function for Generative Adversarial Networks"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Rui","family":"YANG","sequence":"first","affiliation":[{"name":"The University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael","family":"SHU","sequence":"additional","affiliation":[{"name":"Amazon AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hideki","family":"NAKAYAMA","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, \u201cGenerative adversarial nets,\u201d Advances in neural information processing systems, pp.2672-2680, 2014."},{"key":"2","unstructured":"[2] M. Arjovsky, S. Chintala, and L. Bottou, \u201cWasserstein generative adversarial networks,\u201d Int. Conf. Mach. Learn., pp.214-223, 2017."},{"key":"3","unstructured":"[3] S. Liu, O. Bousquet, and K. Chaudhuri, \u201cApproximation and convergence properties of generative adversarial learning,\u201d Advances in Neural Information Processing Systems, vol.30, pp.5545-5553, 2017."},{"key":"4","unstructured":"[4] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A.C. Courville, \u201cImproved training of wasserstein GANs,\u201d Advances in neural information processing systems, pp.5767-5777, 2017."},{"key":"5","unstructured":"[5] L. Mescheder, A. Geiger, and S. Nowozin, \u201cWhich training methods for GANs do actually converge?,\u201d Int. Conf. Mach. Learn., pp.3481-3490, 2018."},{"key":"6","unstructured":"[6] W. Fedus, M. Rosca, B. Lakshminarayanan, A.M. Dai, S. Mohamed, and I. Goodfellow, \u201cMany paths to equilibrium: GANs do not need to decrease a divergence at every step,\u201d Int. Conf. Learning Representations, 2018."},{"key":"7","unstructured":"[7] H. Thanh-Tung, T. Tran, and S. Venkatesh, \u201cImproving generalization and stability of generative adversarial networks,\u201d ICLR 2019: Proc. 7th Int. Conf. Learning Representations, ICLR, 2019."},{"key":"8","unstructured":"[8] N. Kodali, J. Abernethy, J. Hays, and Z. Kira, \u201cOn convergence and stability of GANs,\u201d arXiv preprint arXiv:1705.07215, 2017. 10.48550\/arXiv.1705.07215"},{"key":"9","unstructured":"[9] C. Villani, Optimal transport: old and new, Springer Science & Business Media, 2008. 10.1007\/978-3-540-71050-9"},{"key":"10","unstructured":"[10] A. Jolicoeur-Martineau and I. Mitliagkas, \u201cGradient penalty from a maximum margin perspective,\u201d arXiv preprint arXiv:1910.06922, 2020. 10.48550\/arXiv.1910.06922"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] T. Karras, S. Laine, and T. Aila, \u201cA style-based generator architecture for generative adversarial networks,\u201d Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., pp.4401-4410, 2019. 10.1109\/CVPR.2019.00453","DOI":"10.1109\/CVPR.2019.00453"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, and T. Aila, \u201cAnalyzing and improving the image quality of stylegan,\u201d Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., pp.8110-8119, 2020. 10.1109\/CVPR42600.2020.00813","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"13","unstructured":"[13] T. Karras, M. Aittala, J. Hellsten, S. Laine, J. Lehtinen, and T. Aila, \u201cTraining generative adversarial networks with limited data,\u201d arXiv preprint arXiv:2006.06676, 2020. 10.48550\/arXiv.2006.06676"},{"key":"14","unstructured":"[14] V. Nair and G.E. Hinton, \u201cRectified linear units improve restricted boltzmann machines,\u201d Proc. 27th Int. Conf. Mach. Learn. (ICML-10), pp.807-814, 2010."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDelving deep into rectifiers: Surpassing human-level performance on imagenet classification,\u201d Proc. IEEE Int. Conf. Comput. Vis., pp.1026-1034, 2015. 10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"16","unstructured":"[16] A.L. Maas, A.Y. Hannun, and A.Y. Ng, \u201cRectifier nonlinearities improve neural network acoustic models,\u201d in ICML Workshop on Deep Learning for Audio, Speech and Language Processing, Citeseer, 2013."},{"key":"17","unstructured":"[17] T. Miyato, T. Kataoka, M. Koyama, and Y. Yoshida, \u201cSpectral normalization for generative adversarial networks,\u201d Int. Conf. Learning Representations, 2018."},{"key":"18","unstructured":"[18] A. Brock, J. Donahue, and K. Simonyan, \u201cLarge scale GAN training for high fidelity natural image synthesis,\u201d Int. Conf. Learning Representations, 2019."},{"key":"19","unstructured":"[19] A. Radford, L. Metz, and S. Chintala, \u201cUnsupervised representation learning with deep convolutional generative adversarial networks,\u201d arXiv preprint arXiv:1511.06434, 2015. 10.48550\/arXiv.1511.06434"},{"key":"20","unstructured":"[20] H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, \u201cSelf-attention generative adversarial networks,\u201d Int. Conf. Mach. Learn., pp.7354-7363, PMLR, 2019."},{"key":"21","unstructured":"[21] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014. 10.48550\/arXiv.1412.6980"},{"key":"22","unstructured":"[22] A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer, \u201cAutomatic differentiation in pytorch,\u201d 2017."},{"key":"23","unstructured":"[23] M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, \u201cGans trained by a two time-scale update rule converge to a local nash equilibrium,\u201d Advances in neural information processing systems, pp.6626-6637, 2017."},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] A. Borji, \u201cPros and cons of GAN evaluation measures,\u201d Computer Vision and Image Understanding, vol.179, pp.41-65, Feb. 2019. 10.1016\/j.cviu.2018.10.009","DOI":"10.1016\/j.cviu.2018.10.009"},{"key":"25","unstructured":"[25] T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, \u201cImproved techniques for training GANs,\u201d Advances in neural information processing systems, pp.2234-2242, 2016."},{"key":"26","unstructured":"[26] A. Jolicoeur-Martineau, \u201cThe relativistic discriminator: a key element missing from standard GAN,\u201d Int. Conf. Learning Representations, 2019."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] J. Wu, Z. Huang, J. Thoma, D. Acharya, and L. Van Gool, \u201cWasserstein divergence for GANs,\u201d Proc. European Conf. Comput. Vis. (ECCV), Sept. 2018. 10.1007\/978-3-030-01228-1_40","DOI":"10.1007\/978-3-030-01228-1_40"},{"key":"28","unstructured":"[28] Y.L. Wu, H.H. Shuai, Z.R. Tam, and H.Y. Chiu, \u201cGradient normalization for generative adversarial networks,\u201d Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp.6373-6382, 2021. 10.1109\/ICCV48922.2021.00631"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/9\/E105.D_2022EDP7019\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T04:55:12Z","timestamp":1662180912000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/9\/E105.D_2022EDP7019\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":28,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022edp7019","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,1]]},"article-number":"2022EDP7019"}}