A scale-conditioned latent diffusion model with a cross-magnification conditioning space generates multi-scale pathology patches, large coherent 4096x4096 images, and super-resolved samples, with denoiser features that improve MIL classification.
Scaling vision transformers to gigapixel images via hierarchical self-supervised learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ZoomLDM: Latent Diffusion Model for multi-scale image generation
A scale-conditioned latent diffusion model with a cross-magnification conditioning space generates multi-scale pathology patches, large coherent 4096x4096 images, and super-resolved samples, with denoiser features that improve MIL classification.