Self-Supervised Representation Learning for Astronomical Images

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 codes, trained models, and data can be found at https://portal.nersc.gov/project/dasrepo/self-supervised-learning-sdss

References in corpus (10)

• The 2.5 m Telescope of the Sloan Digital Sky Survey
• Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Photometric redshift estimation via deep learning
• Galaxy Zoo: comparing the demographics of spiral arm number and a new method for correcting redshift bias
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Pushing automated morphological classifications to their limits with the Dark Energy Survey

Cited by in corpus (11)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Practical Galaxy Morphology Tools from Deep Supervised Representation Learning
• Mining for Strong Gravitational Lenses with Self-supervised Learning
• Optimized Photometric Redshifts for the Cosmic Assembly Near-Infrared Deep Extragalactic Legacy Survey (CANDELS)
• Self-supervised Anomaly Detection for New Physics
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Galaxy Spin Classification I: Z-wise vs S-wise Spirals With Chirality Equivariant Residual Network
• An Image Processing approach to identify solar plages observed at 393.37 nm by the Kodaikanal Solar Observatory
• Lenses In VoicE (LIVE): Searching for strong gravitational lenses in the VOICE@VST survey using Convolutional Neural Networks