Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels

Jan Oscar Cross-Zamirski, Praveen Anand, Guy Williams, Elizabeth Mouchet, Yinhai Wang, Carola-Bibiane Schönlieb; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 3800-3809

Abstract

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cross-Zamirski_2023_ICCV, author = {Cross-Zamirski, Jan Oscar and Anand, Praveen and Williams, Guy and Mouchet, Elizabeth and Wang, Yinhai and Sch\"onlieb, Carola-Bibiane}, title = {Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {3800-3809} }