Estimating Galactic Distances From Images Using Self-supervised Representation Learning
This work addresses the challenge of distance estimation in astronomy, offering a more data-efficient solution, though it is incremental as it builds on existing self-supervised techniques.
The paper tackled the problem of estimating galactic distances from images by using a self-supervised learning framework with custom augmentations, achieving accuracy comparable to fully-supervised models with 2-4x less labeled data and outperforming the state-of-the-art supervised method on the SDSS dataset.
We use a contrastive self-supervised learning framework to estimate distances to galaxies from their photometric images. We incorporate data augmentations from computer vision as well as an application-specific augmentation accounting for galactic dust. We find that the resulting visual representations of galaxy images are semantically useful and allow for fast similarity searches, and can be successfully fine-tuned for the task of redshift estimation. We show that (1) pretraining on a large corpus of unlabeled data followed by fine-tuning on some labels can attain the accuracy of a fully-supervised model which requires 2-4x more labeled data, and (2) that by fine-tuning our self-supervised representations using all available data labels in the Main Galaxy Sample of the Sloan Digital Sky Survey (SDSS), we outperform the state-of-the-art supervised learning method.