Self-supervised Learning for Astronomical Image Classification

In Astronomy, a huge amount of image data is generated daily by photometric surveys, which scan the sky to collect data from stars, galaxies and other celestial objects. In this paper, we propose a technique to leverage unlabeled astronomical images to pre-train deep convolutional neural networks, in order to learn a domain-specific feature extractor which improves the results of machine learning techniques in setups with small amounts of labeled data available. We show that our technique produces results which are in many cases better than using ImageNet pre-training.

[1]  Yoshua Bengio,et al.  Deep Learning of Representations for Unsupervised and Transfer Learning , 2011, ICML Unsupervised and Transfer Learning.

[2]  John L. Tonry,et al.  Machine-learned Identification of RR Lyrae Stars from Sparse, Multi-band Data: The PS1 Sample , 2016, 1611.08596.

[3]  Miguel A. Aragon-Calvo.  Self-supervised Learning with Physics-aware Neural Networks I: Galaxy Model Fitting , 2020 .

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Yannick Mellier,et al.  The EFIGI catalogue of 4458 nearby galaxies with detailed morphology , 2011, 1103.5734.

[6]  Canada.,et al.  Data Mining and Machine Learning in Astronomy , 2009, 0906.2173.

[7]  A. Molino,et al.  The S-PLUS: a star/galaxy classification based on a Machine Learning approach , 2019, 1909.08626.

[8]  Ce Zhang,et al.  Using transfer learning to detect galaxy mergers , 2018, Monthly Notices of the Royal Astronomical Society.

[9]  A. Szalay,et al.  Preparing Red-Green-Blue (RGB) Images from CCD Data , 2003 .

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Sander Dieleman,et al.  Rotation-invariant convolutional neural networks for galaxy morphology prediction , 2015, ArXiv.

[13]  Farhan Feroz,et al.  SKYNET: an efficient and robust neural network training tool for machine learning in astronomy , 2013, ArXiv.

[14]  D. A. Kann,et al.  The Southern Photometric Local Universe Survey (S-PLUS): improved SEDs, morphologies, and redshifts with 12 optical filters , 2019, Monthly Notices of the Royal Astronomical Society.

[15]  Nina Sumiko Tomita Hirata,et al.  Deep Learning for Astronomical Object Classification: A Case Study , 2020, VISIGRAPP.

[16]  Matthijs Douze,et al.  Deep Clustering for Unsupervised Learning of Visual Features , 2018, ECCV.

[17]  Nikos Komodakis,et al.  Unsupervised Representation Learning by Predicting Image Rotations , 2018, ICLR.

[18]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[19]  Jon Kleinberg,et al.  Transfusion: Understanding Transfer Learning for Medical Imaging , 2019, NeurIPS.

[20]  Dawn Song,et al.  Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty , 2019, NeurIPS.

[21]  K. Abazajian,et al.  THE SEVENTH DATA RELEASE OF THE SLOAN DIGITAL SKY SURVEY , 2008, 0812.0649.

[22]  Andrew J. Connolly,et al.  Statistics, Data Mining, and Machine Learning in Astronomy , 2014 .

[23]  E. Bertin,et al.  SExtractor: Software for source extraction , 1996 .

[24]  Adi Shraibman,et al.  Rank, Trace-Norm and Max-Norm , 2005, COLT.

[25]  Michael J. Drinkwater,et al.  Mathematical Morphology: Star/Galaxy Differentiation & Galaxy Morphology Classification , 2006, Publications of the Astronomical Society of Australia.

[26]  C. Lintott,et al.  Galaxy Zoo: morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey , 2008, 0804.4483.

[27]  Kristian Zarb Adami,et al.  Machine Learning for Galaxy Morphology Classification , 2010, ArXiv.

[28]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[29]  J. J.,et al.  The Realm of the Nebulae , 1936, Nature.

[30]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[31]  Anders Krogh,et al.  A Simple Weight Decay Can Improve Generalization , 1991, NIPS.

[32]  Edward J. Kim,et al.  Star-galaxy Classification Using Deep Convolutional Neural Networks , 2016, ArXiv.

[33]  Alexei A. Efros,et al.  Unsupervised Visual Representation Learning by Context Prediction , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[34]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .