{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:22:45Z","timestamp":1760235765497,"version":"build-2065373602"},"reference-count":31,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Mode collapse has always been a fundamental problem in generative adversarial networks. The recently proposed Zero Gradient Penalty (0GP) regularization can alleviate the mode collapse, but it will exacerbate a discriminator\u2019s misjudgment problem, that is the discriminator judges that some generated samples are more real than real samples. In actual training, the discriminator will direct the generated samples to point to samples with higher discriminator outputs. The serious misjudgment problem of the discriminator will cause the generator to generate unnatural images and reduce the quality of the generation. This paper proposes Real Sample Consistency (RSC) regularization. In the training process, we randomly divided the samples into two parts and minimized the loss of the discriminator\u2019s outputs corresponding to these two parts, forcing the discriminator to output the same value for all real samples. We analyzed the effectiveness of our method. The experimental results showed that our method can alleviate the discriminator\u2019s misjudgment and perform better with a more stable training process than 0GP regularization. Our real sample consistency regularization improved the FID score for the conditional generation of Fake-As-Real GAN (FARGAN) from 14.28 to 9.8 on CIFAR-10. Our RSC regularization improved the FID score from 23.42 to 17.14 on CIFAR-100 and from 53.79 to 46.92 on ImageNet2012. Our RSC regularization improved the average distance between the generated and real samples from 0.028 to 0.025 on synthetic data. The loss of the generator and discriminator in standard GAN with our regularization was close to the theoretical loss and kept stable during the training process.<\/jats:p>","DOI":"10.3390\/e23091231","type":"journal-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T07:52:14Z","timestamp":1632124334000},"page":"1231","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Real Sample Consistency Regularization for GANs"],"prefix":"10.3390","volume":"23","author":[{"given":"Xiangde","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Sciences, Northeastern University, Shenyang 110819, China"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Sciences, Northeastern University, Shenyang 110819, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,19]]},"reference":[{"key":"ref_1","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C., and Bengio, Y. (2014, January 8\u201313). Generative Adversarial Nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_2","unstructured":"Jolicoeur-Martineau, A. (2019, January 6\u20139). The relativistic discriminator: A key element missing from standard GAN. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_3","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., and Odena, A. (2019, January 10\u201315). Self-Attention Generative Adversarial Networks. Proceedings of the 36th International Conference on Machine Learning, Los Angeles, CA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Gu, J., Shen, Y., and Zhou, B. (2020, January 13\u201319). Image processing using multi-code GaN prior. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., and Zhou, B. (2020, January 13\u201319). Interpreting the latent space of GANs for semantic face editing. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref_6","unstructured":"Brock, A., Donahue, J., and Simonyan, K. (2019, January 6\u20139). Large Scale GAN Training for High Fidelity Natural Image Synthesis. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., and Wang, Z. (2017, January 21\u201326). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref_8","unstructured":"Shaham, T.R., Dekel, T., and Michaeli, T. (November, January 27). SinGAN: Learning a generative model from a single natural image. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., and Choo, J. (2018, January 18\u201323). StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref_10","unstructured":"Miyato, T., Kataoka, T., Koyama, M., and Yoshida, Y. (May, January 30). Spectral normalization for generative adversarial networks. Proceedings of the 6th International Conference on Learning Representations, ICLR 2018\u2014Conference Track Proceedings, Vancouver, BC, Canada."},{"key":"ref_11","unstructured":"Karras, T., Aila, T., Laine, S., and Lehtinen, J. (May, January 30). Progressive Growing of GANs for Improved Quality, Stability, and Variation. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., and Aila, T. (2019, January 15\u201320). A Style-Based Generator Architecture for Generative Adversarial Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref_13","unstructured":"Thanh-Tung, H., Venkatesh, S., and Tran, T. (2019, January 6\u20139). Improving generalization and stability of generative adversarial networks. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_14","unstructured":"Mescheder, L., Geiger, A., and Nowozin, S. (2018, January 10\u201315). Which training methods for GANs do actually converge?. Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Tao, S., and Wang, J. (2020, January 13\u201319). Alleviation of gradient exploding in GANs: Fake can be real. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00127"},{"key":"ref_16","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6\u201311). Wasserstein generative adversarial networks. Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, Australia."},{"key":"ref_17","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. (2017, January 4\u20139). Improved Training of Wasserstein GANs. Proceedings of the 31st International Conference on Neural Information Processing Systems NIPS\u201917, Long Beach, CA, USA."},{"key":"ref_18","unstructured":"Zhang, H., Zhang, Z., Odena, A., and Lee, H. (2020, January 26\u201330). Consistency Regularization for Generative Adversarial Networks. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., and Smolley, S.P. (2017, January 22\u201329). Least Squares Generative Adversarial Networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1198\/016214507000000617","article-title":"Robust Truncated Hinge Loss Support Vector Machines","volume":"102","author":"Wu","year":"2007","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_22","unstructured":"S\u00f8nderby, C.K., Caballero, J., Theis, L., Shi, W., and Husz\u00e1r, F. (2017). Amortised map inference for image super-resolution. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s00591-010-0080-8","article-title":"Exponential moving average versus moving exponential average","volume":"58","author":"Klinker","year":"2011","journal-title":"Math. Semesterber."},{"key":"ref_24","unstructured":"Metz, L., Poole, B., Pfau, D., and Sohl-Dickstein, J. (2016). Unrolled generative adversarial networks. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Kulharia, V., Namboodiri, V.P., Torr, P.H.S., and Dokania, P.K. (2018, January 18\u201323). Multi-Agent Diverse Generative Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00888"},{"key":"ref_26","unstructured":"Hoang, Q., Nguyen, T.D., Le, T., and Phung, D. (May, January 30). MGAN: Training generative adversarial nets with multiple generators. Proceedings of the 6th International Conference on Learning Representations, ICLR 2018\u2014Conference Track Proceedings, Vancouver, BC, Canada."},{"key":"ref_27","unstructured":"Arora, S., Ge, R., Liang, Y., Ma, T., and Zhang, Y. (2017, January 6\u201311). Generalization and Equilibrium in Generative Adversarial Nets (GANs). Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_28","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016, January 5\u201310). Improved techniques for training GANs. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain."},{"key":"ref_29","unstructured":"Radford, A., Metz, L., and Chintala, S. (2016, January 2\u20134). Unsupervised representation learning with deep convolutional generative adversarial networks. Proceedings of the 4th International Conference on Learning Representations, ICLR 2016\u2014Conference Track Proceedings, San Juan, PR, USA."},{"key":"ref_30","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017, January 4\u20139). GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_31","unstructured":"Petzka, H., Fischer, A., and Lukovnikov, D. (May, January 30). On the regularization of Wasserstein GANs. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/9\/1231\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:02:20Z","timestamp":1760166140000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/9\/1231"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":31,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["e23091231"],"URL":"https:\/\/doi.org\/10.3390\/e23091231","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2021,9,19]]}}}