Self-supervised similarity search for large scientific datasets
This work addresses the challenge of efficiently analyzing massive unlabeled datasets for astronomers and scientists, though it is incremental as it applies existing self-supervised techniques to a new domain.
The authors tackled the problem of exploring large unlabeled scientific datasets by developing a self-supervised learning method to create low-dimensional representations for 42 million galaxy images, resulting in a publicly released interactive similarity search tool that enables rapid discovery of rare objects and accelerates crowd-sourcing campaigns.
We present the use of self-supervised learning to explore and exploit large unlabeled datasets. Focusing on 42 million galaxy images from the latest data release of the Dark Energy Spectroscopic Instrument (DESI) Legacy Imaging Surveys, we first train a self-supervised model to distill low-dimensional representations that are robust to symmetries, uncertainties, and noise in each image. We then use the representations to construct and publicly release an interactive semantic similarity search tool. We demonstrate how our tool can be used to rapidly discover rare objects given only a single example, increase the speed of crowd-sourcing campaigns, and construct and improve training sets for supervised applications. While we focus on images from sky surveys, the technique is straightforward to apply to any scientific dataset of any dimensionality. The similarity search web app can be found at https://github.com/georgestein/galaxy_search