BIDS Machine Learning and Science Forum
Date: Monday, March 8, 2021
Time: 11:00 AM - 12:00 PM Pacific Time
Location: Participate remotely using this Zoom link
Self-Supervised Representation Learning for Astronomical Images
Speaker: George Stein, Postdoctoral Researcher, Berkeley Center For Cosmological Physics (BCCP) and Berkeley Lab
Abstract: Sky surveys are the largest data generators in astronomy, making automated tools for extracting meaningful scientific information an absolute necessity. We show that, without the need for labels, self-supervised learning recovers representations of sky survey images that are semantically useful for a variety of scientific tasks. These representations can be directly used as features, or fine-tuned, to outperform supervised methods trained only on labeled data. We apply a contrastive learning framework on multi-band galaxy photometry from the Sloan Digital Sky Survey (SDSS), to learn image representations. We then use them for galaxy morphology classification, and fine-tune them for photometric redshift estimation, using labels from the Galaxy Zoo 2 dataset and SDSS spectroscopy. In both downstream tasks, using the same learned representations, we outperform the supervised state- of-the-art results, and we show that our approach can achieve the accuracy of supervised models while using 2-4 times fewer labels for training.
The BIDS Machine Learning and Science Forum meets biweekly to discuss current applications across a wide variety of research domains in the physical sciences and beyond. These active sessions bring together domain scientists, statisticians, and computer scientists who are either developing state-of-the-art methods or are interested in applying these methods in their research. This Forum is organized by BIDS Faculty Affiliate Uroš Seljak (professor of Physics at UC Berkeley), BIDS Research Affiliate Ben Nachman (Physicist at Lawrence Berkeley National Laboratory), Vanessa Böhm and Ben Erichson. All interested members of the UC Berkeley and Berkeley Lab communities are welcome and encouraged to attend. To receive email notifications about upcoming meetings, or to request more information, please contact email@example.com.