3 papers
cs.CV2026
Deterministic Mode Proposals: An Efficient Alternative to Generative Sampling for Ambiguous Segmentation
Sebastian Gerard, Josephine Sullivan
Many segmentation tasks, such as medical image segmentation or future state prediction, are inherently ambiguous, meaning that multiple predictions are equally correct. Current met…
cs.CV2026
Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free Methods
Sebastian Gerard, Josephine Sullivan
Predicting future states in uncertain environments, such as wildfire spread, medical diagnosis, or autonomous driving, requires models that can consider multiple plausible outcomes…
cs.CV2026
Diffusion Representations for Fine-Grained Image Classification: A Marine Plankton Case Study
A. Nieto Juscafresa, Ã. Mazcuñán Herreros, J. Sullivan
Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for…