Abstract
AI Generated Content (AIGC) is becoming phenomenally prominent and impactful. One of the key generative algorithms used in AIGC is the diffusion model which is widely used in generative images and audio. In comparison with other generative methods such as GAN (Generative Adversarial Network) and VAE (Variational Auto Encoder), diffusion models can generate samples of higher quality. To further improve diffusion models, especially in terms of sampling speed, we propose an evolutionary algorithm in this paper. That is to enhance the noise scheduler of the diffusion framework, thereby improving both performance and sampling speed. This is the first diffusion model that incorporates evolutionary algorithms. Our experiments show that evolved schedulers can bring concrete improvement in the generative process.
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
Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. Stat 1050, 17 (2017)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780–8794 (2021)
Franceschi, J.Y., et al.: Unifying GANs and score-based diffusion as generative particle models. arXiv preprint arXiv:2305.16150 (2023)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27 (2014)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Stat 1050, 9 (2015)
Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840–6851 (2020)
Huang, R., et al.: FastDiff: a fast conditional diffusion model for high-quality speech synthesis. In: IJCAI (2022)
Kim, D., Kim, Y., Kang, W., Moon, I.C.: Refining generative process with discriminator guidance in score-based diffusion models. Comput. Vis. Pattern Recogn. (2022)
Krizhevsky, A., et al.: Learning multiple layers of features from tiny images (2009)
Lam, M.W., Wang, J., Su, D., Yu, D.: BDDM: bilateral denoising diffusion models for fast and high-quality speech synthesis. In: ICLR (2022)
Lee, S.G., et al.: PriorGrad: Improving conditional denoising diffusion models with data-driven adaptive prior. In: ICLR (2021)
Luhman, E., Luhman, T.: Knowledge distillation in iterative generative models for improved sampling speed. arXiv preprint arXiv:2101.02388 (2021)
Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162–8171. PMLR (2021)
von Platen, P., et al.: Diffusers: State-of-the-art diffusion models. https://github.com/huggingface/diffusers (2022)
Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: ICLR (2022)
San-Roman, R., Nachmani, E., Wolf, L.: Noise estimation for generative diffusion models. Comput. Vis. Pattern Recogn. (2021)
Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)
Song, Y., Ermon, S.: Improved techniques for training score-based generative models. Adv. Neural. Inf. Process. Syst. 33, 12438–12448 (2020)
Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)
Wang, Z., Zheng, H., He, P., Chen, W., Zhou, M.: Diffusion-GAN: Training GANs with diffusion. arXiv preprint arXiv:2206.02262 (2022)
Xiao, Z., Kreis, K., Vahdat, A.: Tackling the generative learning trilemma with denoising diffusion GANs. In: ICLR (2022)
Yeom, T., Lee, M.: DuDGAN: improving class-conditional GANs via dual-diffusion. arXiv preprint arXiv:2305.14849 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Z., Song, A., Sabar, N., Li, W. (2024). Evolving a Better Scheduler for Diffusion Models. In: Liu, F., Sadanandan, A.A., Pham, D.N., Mursanto, P., Lukose, D. (eds) PRICAI 2023: Trends in Artificial Intelligence. PRICAI 2023. Lecture Notes in Computer Science(), vol 14326. Springer, Singapore. https://doi.org/10.1007/978-981-99-7022-3_37
Download citation
DOI: https://doi.org/10.1007/978-981-99-7022-3_37
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7021-6
Online ISBN: 978-981-99-7022-3
eBook Packages: Computer ScienceComputer Science (R0)