ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
Merged summary
TL;DR - ROMS-IMLE is a minimalist, single-step image generator that pairs Implicit Maximum Likelihood Estimation with a moderately sized convolutional network. It challenges the assumption that high-quality generation requires iterative denoising or transformer architectures.
- Avoids variational inference, adversarial training, numerical integration, and iterative denoising.
- Generates samples in one step for fast, parameter-efficient inference.
- Achieves an FID of 2.56 on ImageNet 256 while maintaining good precision and recall.
- Suggests gradual noise-to-data transformations are not essential for competitive image generation.
Sources (1)
ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
TL;DR - ROMS-IMLE is a minimalist, single-step image generator that pairs Implicit Maximum Likelihood Estimation with a moderately sized convolutional network. It challenges the assumption that high-quality generation requires iterative denoising or transformer architectures.
- Avoids variational inference, adversarial training, numerical integration, and iterative denoising.
- Generates samples in one step for fast, parameter-efficient inference.
- Achieves an FID of 2.56 on ImageNet 256 while maintaining good precision and recall.
- Suggests gradual noise-to-data transformations are not essential for competitive image generation.