Metraipolis › archive › dc_96b4dbca9cc6

Coarse to Fine: Iterative Adversarial Neural Cellular Automata for Medical Image Synthesis — arXiv:2608.28909

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28909
License (as archived)
CC0-1.0
Archived
2026-10-17T09:53:25.116Z
SHA-256 of the archived text
ef3db11f142c54b6f95c2152936437a17b374a40bd0eac4bef48eb2f438d7367
Stable URL of this page
https://metraipolis.com/documento/dc_96b4dbca9cc6

How to cite

Coarse to Fine: Iterative Adversarial Neural Cellular Automata for Medical Image Synthesis — arXiv:2608.28909 — arXiv (en), https://arxiv.org/abs/2608.28909 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96b4dbca9cc6 (Metraipolis archive dc_96b4dbca9cc6, sha256 ef3db11f142c54b6f95c2152936437a17b374a40bd0eac4bef48eb2f438d7367)
BibTeX
@misc{dc96b4dbca9cc6,
  title = {Coarse to Fine: Iterative Adversarial Neural Cellular Automata for Medical Image Synthesis — arXiv:2608.28909},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28909},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96b4dbca9cc6; sha256 ef3db11f142c54b6f95c2152936437a17b374a40bd0eac4bef48eb2f438d7367},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28909. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large-scale, publicly available datasets have driven advances in deep learning, but privacy and legal restrictions often limit data sharing in medical imaging. Synthetic data generation offers a privacy-friendly alternative to enable the training of high-performance models on health data. While most state-of-the-art generative models produce high-quality images, they remain computationally expensive, which limits their applicability on resource-constrained hardware. We propose StyleGANCA, the first lightweight general-purpose NCA-based generative adversarial network. The architecture integrates a StyleGAN-inspired mapping network and adaptive style modulation into a multi-scale NCA synthesis process, enabling latent-controlled image generation through iterative local interactions. We evaluate StyleGANCA on BloodMNIST and PathMNIST against adversarial, variational, diffusion, and NCA-based baselines. Experimental results demonstrate that StyleGANCA achieves competitive image quality with substantially fewer parameters than baseline architectures, achieving the best FID and KID scores on PathMNIST with only 617k parameters. Furthermore, downstream experiments show that the generated images preserve class-specific information and effectively support the training of multi-class classifiers. Our code is publicly available at: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28909 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T09:28:47.965Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).