AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Controllable Latent Space Augmentation for Digital Pathology

Sofiène Boutaj, Marin Scalbert, Pierre Marza, Florent Couzinie-Devy, Maria Vakalopoulou, Stergios Christodoulidis

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add WSI-wise HistAug augmentationABMIL-family MIL on UNI · UCEC (10% train)C-index: 59.3 -> 63.2Improved
add WSI-wise HistAug augmentationMIL on CONCH · UCEC (10% train)C-index: 58.6 -> 64.9Improved
add WSI-wise HistAug augmentationMIL on UNI · BRCA (10% train)AUC: 86.1 -> 88.3Improved
add WSI-wise HistAug augmentationMIL on CONCH · NSCLC (10% train)AUC: 92.8 -> 94.6Improved
add instance-wise HistAug augmentationMIL on UNI · BLCA (100% train)C-index: 54.5 -> 60.3Improved
replace Gaussian noise perturbation with learned HistAug (WSI) augmentation (ablation)MIL on CONCH · KIRC (10% train)C-index: +6.4Improved
replace Gaussian noise perturbation with learned HistAug (WSI) augmentation (ablation)MIL on UNI · BRCA (100% train)AUC: -0.5No clear effect
add noise perturbation to features (ablation)MIL · 10% and 100% trainperformanceNo clear effect
apply 10x-trained generator at 20x magnificationMIL on CONCH · UCEC (20x)C-index: 60.5 -> 67.1Improved
add chunking of input embedding into tokens (ablation)HistAug generator · generator trainingtraining MSE lossImproved
add AugDiff augmentationDSMIL on UNI · BRCA/NSCLC classification (10% train)AUC: 83.2 -> 76.2Hurt
add patch augmentation (PAug)MIL on UNI · classification (100% train)AUC: 95.4 -> 93.7Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy