EUVIMEDEUVIMED entdecken
Crossref

Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models

Francisco Caetano, Christiaan Viviers, Peter H.N. de With, Fons Van der Sommen

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2498-2506

DOI: 10.1609/aaai.v40i4.37236 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Francisco Caetano und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Flow Matching has emerged as a powerful framework for learning continuous transformations between distributions, enabling high-fidelity generative modeling. This work introduces Symmetrical Flow Matching (SymmFlow), a new formulation that unifies semantic segmentation, classification, and image generation within a single model. Using a symmetric learning objective, SymmFlow models forward and reverse transformations jointly, ensuring bi-directional consistency, while preserving sufficient entropy for generative diversity. A new training objective is introduced to explicitly retain semantic information across flows, featuring efficient sampling while preserving semantic structure, allowing for one-step segmentation and classification without iterative refinement. Unlike previous approaches that impose strict one-to-one mapping between masks and images, SymmFlow generalizes to flexible conditioning, supporting both pixel-level and image-level class labels. Experimental results on various benchmarks demonstrate that SymmFlow achieves state-of-the-art performance on semantic image synthesis, obtaining FID scores of 11.9 on CelebAMask-HQ and 7.0 on COCO-Stuff with only 25 inference steps. Additionally, it delivers competitive results on semantic segmentation and shows promising capabilities in classification tasks.

Zitieren

APA

Caetano, F., Viviers, C., With, P. H. D., & Sommen, F. V. D. (2026). Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2498-2506. https://doi.org/10.1609/aaai.v40i4.37236

Vancouver

Caetano F, Viviers C, With PHD, Sommen FVD. Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2498-2506. doi:10.1609/aaai.v40i4.37236

BibTeX
@article{Caetano2026,
  author = {Caetano, Francisco and Viviers, Christiaan and With, Peter H.N. de and Sommen, Fons Van der},
  title = {Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {4},
  pages = {2498--2506},
  doi = {10.1609/aaai.v40i4.37236}
}
Kostenlos starten →