Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology

arXiv:2404.10242v1 Announce Type: cross
Abstract: Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images. This work explores the scaling properties of weakly supervised classifiers and self-supervised masked autoencoders (MAEs) when training with increasingly larger model backbones and microscopy datasets. Our results show that ViT-based MAEs outperform weakly supervised classifiers on a variety of tasks, achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from …

abstract arxiv autoencoders biology cellular challenge classifiers cs.ai cs.cv cs.lg datasets images microscopy research scalable scale scaling training type work