Metraipolis › archive › dc_15c2c8ca539f
MedNet and U$^2$-ViT: A Nested Vision Transformer Diffusion Framework for Diverse Medical Images Generation — arXiv:2611.01605
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01605
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:54:38.642Z
- SHA-256 of the archived text
a7e87cf68ae107bcf961620a60dca94fab2c5e29eb7594099175a7a29b68087c- Stable URL of this page
https://metraipolis.com/documento/dc_15c2c8ca539f
How to cite
MedNet and U$^2$-ViT: A Nested Vision Transformer Diffusion Framework for Diverse Medical Images Generation — arXiv:2611.01605 — arXiv (en), https://arxiv.org/abs/2611.01605 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_15c2c8ca539f (Metraipolis archive dc_15c2c8ca539f, sha256 a7e87cf68ae107bcf961620a60dca94fab2c5e29eb7594099175a7a29b68087c)
BibTeX
@misc{dc15c2c8ca539f,
title = {MedNet and U$^2$-ViT: A Nested Vision Transformer Diffusion Framework for Diverse Medical Images Generation — arXiv:2611.01605},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01605},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_15c2c8ca539f; sha256 a7e87cf68ae107bcf961620a60dca94fab2c5e29eb7594099175a7a29b68087c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01605. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The scarcity of diverse, high-quality medical images remains a significant bottleneck in advancing AI-driven medical diagnostics and treatment planning. Traditional datasets often suffer from class imbalances, limited disease coverage, and insufficient variations in imaging conditions - challenges that hinder the development of robust, generalizable models. To address this, we introduce MedNet, a large-scale, multi-modal text-to-image dataset spanning 61 disease categories with 160 classes, covering both humans and animals. We built this with images from trusted public repositories, ensuring data diversity, quality, and ethical compliance. Additionally, we propose U$^2$-ViT, a novel diffusion-based text-to-image generation architecture arranging Vision Transformers (ViTs) in a nested U-Net structure to enhance the generation of diverse, and high-fidelity medical images. Through extensive experiments, we demonstrate that our model achieves the best Fr'echet Inception Distance (FID) score compared to state-of-the-art models. The source code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.01605 — 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 2026-11-03T18:16:52.940Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).