Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels
This work addresses a specific need in drug discovery for better image reconstruction using class labels, but it is incremental as it adapts existing diffusion methods to a domain-specific setting.
The paper tackled the problem of image-to-image reconstruction in biological microscopy where metadata is available as discrete class labels, by introducing a class-guided diffusion model that improved meaningful content in reconstructed images and outperformed unguided models in downstream tasks.
Image-to-image reconstruction problems with free or inexpensive metadata in the form of class labels appear often in biological and medical image domains. Existing text-guided or style-transfer image-to-image approaches do not translate to datasets where additional information is provided as discrete classes. We introduce and implement a model which combines image-to-image and class-guided denoising diffusion probabilistic models. We train our model on a real-world dataset of microscopy images used for drug discovery, with and without incorporating metadata labels. By exploring the properties of image-to-image diffusion with relevant labels, we show that class-guided image-to-image diffusion can improve the meaningful content of the reconstructed images and outperform the unguided model in useful downstream tasks.