Metraipolis › archive › dc_70da3f6bfb99

MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation — arXiv:2609.15647

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15647
License (as archived)
CC0-1.0
Archived
2026-10-16T01:53:35.974Z
SHA-256 of the archived text
a2ea4c05a94609580b1a55d0bf644245435be2112366fa3844b861d89ac2e8da
Stable URL of this page
https://metraipolis.com/documento/dc_70da3f6bfb99

How to cite

MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation — arXiv:2609.15647 — arXiv (en), https://arxiv.org/abs/2609.15647 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70da3f6bfb99 (Metraipolis archive dc_70da3f6bfb99, sha256 a2ea4c05a94609580b1a55d0bf644245435be2112366fa3844b861d89ac2e8da)
BibTeX
@misc{dc70da3f6bfb99,
  title = {MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation — arXiv:2609.15647},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15647},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70da3f6bfb99; sha256 a2ea4c05a94609580b1a55d0bf644245435be2112366fa3844b861d89ac2e8da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15647. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Medical counterfactual generation modifies images to change model predictions for interpretability. However, existing diffusion-based approaches are often prohibitively slow and memory-intensive, making them difficult to apply in high-resolution settings. Moreover, existing masking strategies are tightly coupled with pixel-space representations, making them incompatible with latent-space diffusion editing. To address these challenges, we propose MedDiME, a latent-space classifier-guided diffusion framework that reduces computational and memory overhead while introducing a latent-compatible, gradient-driven adaptive masking mechanism for spatially precise medical counterfactual generation. Extensive experiments demonstrate that MedDiME achieves high-quality counterfactual generation with significant efficiency gains compared to prior classifier-guided diffusion baselines, achieving up to 40 times faster inference and 13 times lower peak GPU memory usage.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.15647 — 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 2026-10-16T01:25:23.694Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).