Abstract
Generative adversarial networks (GANs) have proven successful in image generation tasks. However, GAN training is inherently unstable. Although many works try to stabilize it by manually modifying GAN architecture, it requires much expertise. Neural architecture search (NAS) has become an attractive solution to search GANs automatically. The early NAS-GANs search only generators to reduce search complexity but lead to a sub-optimal GAN. Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training. To alleviate the instability, we propose an efficient two-stage evolutionary algorithm-based NAS framework to search GANs, namely EAGAN. We decouple the search of G and D into two stages, where stage-1 searches G with a fixed D and adopts the many-to-one training strategy, and stage-2 searches D with the optimal G found in stage-1 and adopts the one-to-one training and weight-resetting strategies to enhance the stability of GAN training. Both stages use the non-dominated sorting method to produce Pareto-front architectures under multiple objectives (e.g., model size, Inception Score (IS), and Fréchet Inception Distance (FID)). EAGAN is applied to the unconditional image generation task and can efficiently finish the search on the CIFAR-10 dataset in 1.2 GPU days. Our searched GANs achieve competitive results (IS = 8.81 ± 0.10, FID = 9.91) on the CIFAR-10 dataset and surpass prior NAS-GANs on the STL-10 dataset (IS = 10.44 ± 0.087, FID = 22.18). Source code: https://github.com/marsggbo/EAGAN.
G. Ying and X. He—Equal contributions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The higher the IS value, the better the GAN performance.
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223. PMLR (2017)
Bissoto, A., Valle, E., Avila, S.: The six fronts of the generative adversarial networks. arXiv preprint arXiv:1910.13076 (2019)
Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2019)
Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (2011)
Costa, V., Lourenço, N., Machado, P.: Coevolution of generative adversarial networks. In: Kaufmann, P., Castillo, P.A. (eds.) EvoApplications 2019. LNCS, vol. 11454, pp. 473–487. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-16692-2_32
Deb, K., Agrawal, S., Pratap, A., Meyarivan, T.: A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II. In: Schoenauer, M., Deb, K., Rudolph, G., Yao, X., Lutton, E., Merelo, J.J., Schwefel, H.-P. (eds.) PPSN 2000. LNCS, vol. 1917, pp. 849–858. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45356-3_83
Doveh, S., Giryes, R.: Degas: Differentiable efficient generator search. arXiv preprint arXiv:1912.00606 (2019)
Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. arXiv preprint arXiv:1808.05377 (2018)
Gao, C., Chen, Y., Liu, S., Tan, Z., Yan, S.: Adversarialnas: adversarial neural architecture search for GANs. In: Proceedings of the CVPR (2020)
Gong, X., Chang, S., Jiang, Y., Wang, Z.: Autogan: neural architecture search for generative adversarial networks. In: Proceedings of the ICCV (2019)
Goodfellow, I., et al.: Generative adversarial nets. Advances in neural information processing systems 27 (2014)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. Advances in neural information processing systems 30 (2017)
He, H., Wang, H., Lee, G.H., Tian, Y.: Probgan: towards probabilistic gan with theoretical guarantees. In: ICLR (2018)
He, X., Zhao, K., Chu, X.: Automl: a survey of the state-of-the-art. Knowl.-Based Syst. 212, 106622 (2021)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Proceedings of the NeurIPS (2017)
Hjelm, R.D., Jacob, A.P., Che, T., Trischler, A., Cho, K., Bengio, Y.: Boundary-seeking generative adversarial networks. arXiv preprint arXiv:1702.08431 (2017)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report (2009)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lin, Q., Fang, Z., Chen, Y., Tan, K.C., Li, Y.: Evolutionary architectural search for generative adversarial networks. IEEE Trans. Emerging Top. Comput. Intell. (2022)
Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L.-J., Fei-Fei, L., Yuille, A., Huang, J., Murphy, K.: Progressive neural architecture search. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 19–35. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_2
Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)
Liu, L., Zhang, Y., Deng, J., Soatto, S.: Dynamically grown generative adversarial networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35(10), pp. 8680–8687 (2021)
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)
Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier gans. In: International Conference on Machine Learning, pp. 2642–2651. PMLR (2017)
Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI, vol. 33 (2019)
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. In: Proceedings of the NeurIPS (2016)
Tian, Y., Shen, L., Su, G., Li, Z., Liu, W.: Alphagan: Fully differentiable architecture search for generative adversarial networks. arXiv preprint arXiv:2006.09134 (2020)
Tian, Y., Wang, Q., Huang, Z., Li, W., Dai, D., Yang, M., Wang, J., Fink, O.: Off-policy reinforcement learning for efficient and effective GAN architecture search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 175–192. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_11
Wang, C., Xu, C., Yao, X., Tao, D.: Evolutionary generative adversarial networks. IEEE Trans. Evol. Comput. 23(6), 921–934 (2019)
Wang, H., Huan, J.: Agan: Towards automated design of generative adversarial networks. arXiv preprint arXiv:1906.11080 (2019)
Wang, W., Sun, Y., Halgamuge, S.: Improving MMD-GAN training with repulsive loss function. In: ICLR (2019)
Xie, L., Chen, X., Bi, K., Wei, L., Xu, Y., Wang, L., Chen, Z., Xiao, A., Chang, J., Zhang, X., et al.: Weight-sharing neural architecture search: a battle to shrink the optimization gap. ACM Comput. Surv. (CSUR) 54(9), 1–37 (2021)
Yang, Z., et al.: Cars: continuous evolution for efficient neural architecture search. In: Proceedings of the CVPR (2020). https://doi.org/10.1109/CVPR42600.2020.00190
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
Acknowledgements
Thanks to the NVIDIA AI Technology Center (NVAITC) for providing the GPU cluster to support our work. BH was supported by the NSFC Young Scientists Fund No. 62006202, Guangdong Basic and Applied Basic Research Foundation No. 2022A1515011652, RGC Early Career Scheme No. 22200720, RGC Research Matching Grant Scheme No. RMGS2022_11_02 and HKBU CSD Departmental Incentive Grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ying, G., He, X., Gao, B., Han, B., Chu, X. (2022). EAGAN: Efficient Two-Stage Evolutionary Architecture Search for GANs. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13676. Springer, Cham. https://doi.org/10.1007/978-3-031-19787-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-19787-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19786-4
Online ISBN: 978-3-031-19787-1
eBook Packages: Computer ScienceComputer Science (R0)