EUVIMEDEUVIMED entdecken
Crossref

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation

Quan Dao, Hao Phung, Trung Tuan Dao, Dimitris N. Metaxas, Anh Tran

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 2654-2662

DOI: 10.1609/aaai.v39i3.32269 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Quan Dao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerous function evaluations in the sampling process. To address these limitations, we introduce a self-corrected flow distillation method that effectively integrates consistency models and adversarial training within the flow-matching framework. This work is a pioneer in achieving consistent generation quality in both few-step and one-step sampling. Our extensive experiments validate the effectiveness of our method, yielding superior results both quantitatively and qualitatively on CelebA-HQ and zero-shot benchmarks on the COCO dataset.

Zitieren

APA

Dao, Q., Phung, H., Dao, T. T., Metaxas, D. N., & Tran, A. (2025). Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 2654-2662. https://doi.org/10.1609/aaai.v39i3.32269

Vancouver

Dao Q, Phung H, Dao TT, Metaxas DN, Tran A. Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):2654-2662. doi:10.1609/aaai.v39i3.32269

BibTeX
@article{Dao2025,
  author = {Dao, Quan and Phung, Hao and Dao, Trung Tuan and Metaxas, Dimitris N. and Tran, Anh},
  title = {Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {2654--2662},
  doi = {10.1609/aaai.v39i3.32269}
}
Kostenlos starten →