Abstract
We propose to use a quality estimator and evolutionary methods to search the latent space of generative adversarial networks trained on small, difficult datasets, or both. The new method leads to the generation of significantly higher quality images while preserving the original generator’s diversity. Human raters preferred an image from the new version with frequency 83.7% for Cats, 74% for FashionGen, 70.4% for Horses, and 69.2% for Artworks - minor improvements for the already excellent GANs for faces. This approach applies to any quality scorer and GAN generator.
B. Roziere and F. Teytaud—Equal contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)
Sbai, O., Elhoseiny, M., Bordes, A., LeCun, Y., Couprie, C.: DesIGN: design inspiration from generative networks. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 37–44. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11015-4_5
Zhu, S., Fidler, S., Urtasun, R., Lin, D., Loy, C.C.: Be your own prada: fashion synthesis with structural coherence. In: ICCV (2017)
Elgammal, A., Liu, B., Elhoseiny, M., Mazzone, M.: Creative adversarial networks. In: ICCC (2017)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)
Park, T., Liu, M., Wang, T., Zhu, J.: Semantic image synthesis with spatially-adaptive normalization. In: CVPR (2019)
Donahue, J., Krähenbühl, P., Darrell, T.: Adversarial feature learning. In: ICLR (2017)
Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., Greenspan, H.: GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing 321, 321–331 (2018)
Nie, D., et al.: Medical image synthesis with context-aware generative adversarial networks. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (2017)
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan (2019)
Noguchi, A., Harada, T.: Image generation from small datasets via batch statistics adaptation. CoRR abs/1904.01774 (2019)
Parimala, K., Channappayya, S.: Quality aware generative adversarial networks. In: Advances in Neural Information Processing Systems, pp. 2948–2958 (2019)
Yi, Z., Chen, Z., Cai, H., Mao, W., Gong, M., Zhang, H.: BSD-GAN: branched generative adversarial network for scale-disentangled representation learning and image synthesis. IEEE Trans. Image Process. (2020)
Roziere, B., et al.: Tarsier: evolving noise injection in super-resolution gans. arXiv preprint arXiv:2009.12177 (2020)
Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., Yosinski, J.: Plug & play generative networks: Conditional iterative generation of images in latent space (2016)
Volz, V., Schrum, J., Liu, J., Lucas, S.M., Smith, A., Risi, S.: Evolving mario levels in the latent space of a deep convolutional generative adversarial network. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2018, pp. 221–228. Association for Computing Machinery, New York (2018)
Giacomello, E., Lanzi, P.L., Loiacono, D.: Searching the latent space of a generative adversarial network to generate doom levels. In: 2019 IEEE Conference on Games (CoG), pp. 1–8 (2019)
Engel, J.H., Hoffman, M., Roberts, A.: Latent constraints: Learning to generate conditionally from unconditional generative models. CoRR abs/1711.05772 (2017)
Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of gans for semantic face editing (2019)
Zhu, J.-Y., Krähenbühl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 597–613. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_36
Mariani, G., Scheidegger, F., Istrate, R., Bekas, C., Malossi, C.: Bagan: data augmentation with balancing gan. arXiv preprint arXiv:1803.09655 (2018)
Gurumurthy, S., Sarvadevabhatla, R.K., Radhakrishnan, V.B.: Deligan: generative adversarial networks for diverse and limited data. CoRR abs/1706.02071 (2017)
Wang, C., Xu, C., Yao, X., Tao, D.: Evolutionary generative adversarial networks. CoRR abs/1803.00657 (2018)
Bontrager, P., Lin, W., Togelius, J., Risi, S.: Deep interactive evolution. In: Liapis, A., Romero Cardalda, J.J., Ekárt, A. (eds.) EvoMUSART 2018. LNCS, vol. 10783, pp. 267–282. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-77583-8_18
Riviere, M., Teytaud, O., Rapin, J., LeCun, Y., Couprie, C.: Inspirational adversarial image generation. arXiv preprint 1906, 11661 (2019)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)
Ye, P., Kumar, J., Kang, L., Doermann, D.: Unsupervised feature learning framework for no-reference image quality assessment. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)
Hosu, V., Lin, H., Sziranyi, T., Saupe, D.: Koniq-10k: an ecologically valid database for deep learning of blind image quality assessment. IEEE Trans. Image Process. 29, 1 (2020)
Hosu, V., Goldlucke, B., Saupe, D.: Effective aesthetics prediction with multi-level spatially pooled features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9375–9383 (2019)
Dang, D.-C., Lehre, P.K.: Self-adaptation of mutation rates in non-elitist populations. In: Handl, J., Hart, E., Lewis, P.R., López-Ibáñez, M., Ochoa, G., Paechter, B. (eds.) PPSN 2016. LNCS, vol. 9921, pp. 803–813. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45823-6_75
Doerr, B., Le, H.P., Makhmara, R., Nguyen, T.D.: Fast genetic algorithms. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 777–784 (2017)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223(2017)
Riviere, M.: Pytorch GAN Zoo (2019). https://GitHub.com/FacebookResearch/pytorch_GAN_zoo
Rapin, J., Teytaud, O.: Nevergrad - A gradient-free optimization platform. https://GitHub.com/FacebookResearch/Nevergrad (2018)
Moxiegushi: Pokegan (2018). https://github.com/moxiegushi/pokeGAN
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)
Rostamzadeh, N., Hosseini, S., Boquet, T., Stokowiec, W., Zhang, Y., Jauvin, C., Pal, C.: Fashion-Gen: The Generative Fashion Dataset and Challenge. Arxiv preprint 1806.08317 (2018)
Huang, X., Liu, M., Belongie, S.J., Kautz, J.: Multimodal unsupervised image-to-image translation. CoRR abs/1804.04732 (2018)
Zhu, J.Y., Zhang, R., Pathak, D., Darrell, T., Efros, A.A., Wang, O., Shechtman, E.: Toward multimodal image-to-image translation. In: Advances in Neural Information Processing Systems, pp. 465–476 (2017)
Acknowledgments
Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), Project-ID 251654672, TRR 161 (Project A05).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Roziere, B. et al. (2021). EvolGAN: Evolutionary Generative Adversarial Networks. In: Ishikawa, H., Liu, CL., Pajdla, T., Shi, J. (eds) Computer Vision – ACCV 2020. ACCV 2020. Lecture Notes in Computer Science(), vol 12625. Springer, Cham. https://doi.org/10.1007/978-3-030-69538-5_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-69538-5_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69537-8
Online ISBN: 978-3-030-69538-5
eBook Packages: Computer ScienceComputer Science (R0)