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 public databases. Additionally, we develop a new channel-agnostic MAE architecture (CA-MAE) that allows for inputting images of different numbers and orders of channels at inference time. We demonstrate that CA-MAEs effectively generalize by inferring and evaluating on a microscopy image dataset (JUMP-CP) generated under different experimental conditions with a different channel structure than our pretraining data (RPI-93M). Our findings motivate continued research into scaling self-supervised learning on microscopy data in order to create powerful foundation models of cellular biology that have the potential to catalyze advancements in drug discovery and beyond. Relevant code and select models released with this work can be found at: https://github.com/recursionpharma/maes_microscopy.

This study considers the problem of indoor localisation in which the authors try to generate the radio map of the environment based on both labelled and unlabelled measurements (i.e. measurements with and without information about the location that they have been collected). In such problems, the method that has been used for radio‐map generation as well as the quality of the measurements (the received signal strength from different environment's WiFi Access Points) are very critical in the overall accuracy of the generated radio map. In this study, they apply two of the well‐known graph‐based signal processing schemes (namely iterative least square reconstruction and graph‐based label propagation) for polishing the input data, determining the outliers and radio‐map generation. Experimental results show the superior performance of the proposed method compared to previous schemes.