Contextual learning is nearly all you need

In another article, Sunghoon Kwon and colleagues show (Y. Lee et al. As explained by Faisal Mahmood and co-authors in an associated News & Views (G. In another research article in this issue, Mahmood and colleagues show another application of self-supervised learning: searching and retrieving gigapixel whole-slide images (Figure 1) at speeds that are independent of the size of the repository (C. To search for a tissue patch, rather than querying against every slide in the dataset, a variational autoencoder (a probabilistic generative model that learns latent representations of the data) is trained to represent select patches from each slide as a set of codes in a manner that the patches with the highest chances of matching the query can be retrieved by leveraging uncertainty-based ranking and a tree data structure for speed efficiency and scalability.