Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change
Shuntaro Okada, Kenji Doi, Ryota Yoshihashi +2
We propose a general framework for optimizing noise schedules in diffusion models, applicable to both training and sampling. Our method enforces a constant rate of change in the pr…
cs.CV2023
Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
Ryota Yoshihashi, Yuya Otsuka, Kenji Doi +2
The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images. In semantic segmentation, one promising appro…