Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels
- Resource Type
- Conference
- Authors
- Cross-Zamirski, Jan Oscar; Anand, Praveen; Williams, Guy; Mouchet, Elizabeth; Wang, Yinhai; Schonlieb, Carola-Bibiane
- Source
- 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) ICCVW Computer Vision Workshops (ICCVW), 2023 IEEE/CVF International Conference on. :3802-3811 Oct, 2023
- Subject
- Computing and Processing
Engineering Profession
General Topics for Engineers
Signal Processing and Analysis
Drugs
Biological system modeling
Microscopy
Conferences
Noise reduction
Metadata
Probabilistic logic
- Language
- ISSN
- 2473-9944
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.