Abstract:
We examine the capability of generative models to produce realistic galaxy images. We show that mixing generated data with the original data improves the robustness in do...Show MoreMetadata
Abstract:
We examine the capability of generative models to produce realistic galaxy images. We show that mixing generated data with the original data improves the robustness in downstream machine learning tasks. We focus on three different data sets: analytical Sérsic profiles, real galaxies from the COSMOS survey, and galaxy images produced with the SKIRT code, from the IllustrisTNG simulation. We quantify the performance of each generative model, using the Wasserstein distance between the distributions of morphological properties (e.g. the Gini-coefficient, the asymmetry, and ellipticity), the surface brightness distribution on various scales (as encoded by the power spectrum), the bulge statistic, and the colour for the generated and source data sets. With an average Wasserstein distance (Fréchet Inception Distance) of 7.19 × 10−2 (0.55), 5.98 × 10−2 (1.45), and 5.08 × 10−2 (7.76) for the Sérsic, COSMOS and SKIRT data set, respectively, our best models convincingly reproduce even the most complicated galaxy properties and create images that are visually indistinguishable from the source data. We demonstrate that by supplementing the training data set with generated data, it is possible to significantly improve the robustness against domain-shifts and out-of-distribution data. In particular, we train a convolutional neural network to denoise a data set of mock observations. By mixing generated images into the original training data, we obtain an improvement of 11 and 45 per cent in the model performance regarding domain-shifts in the physical pixel size and background noise level, respectively.
Published in: Monthly Notices of the Royal Astronomical Society ( Volume: 515, Issue: 1, April 2022)
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- Index Terms
- Machine Learning ,
- Galaxy Images ,
- Neural Network ,
- Training Data ,
- Training Dataset ,
- Convolutional Neural Network ,
- Denoising ,
- Computer Vision ,
- Power Spectrum ,
- Domain Shift ,
- Point Spread Function ,
- Physical Size ,
- Morphological Measurements ,
- Variational Autoencoder ,
- Source Dataset ,
- Inception Distance ,
- Fréchet Inception Distance ,
- StyleGAN ,
- Physical Pixel Size ,
- Adversarial Neural Network ,
- Compressed Representation ,
- Physical Scale ,
- Average Power Spectrum ,
- Reconstruction Loss ,
- Kullback-Leibler ,
- Effective Radius ,
- Feature Extraction Network ,
- Color Distribution ,
- Residual Block ,
- Mean Square Error ,
- Background Noise ,
- Data Augmentation ,
- Weighting Factor ,
- Linear Interpolation ,
- Latent Representation ,
- Additional Channels ,
- Decrease In Loss ,
- Decrease In Error ,
- Latent Vector ,
- Wasserstein Distance ,
- Machine Learning Models ,
- Image Rotation ,
- Max Planck Society ,
- Morphological Parameters
- Author Keywords
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- Index Terms
- Machine Learning ,
- Galaxy Images ,
- Neural Network ,
- Training Data ,
- Training Dataset ,
- Convolutional Neural Network ,
- Denoising ,
- Computer Vision ,
- Power Spectrum ,
- Domain Shift ,
- Point Spread Function ,
- Physical Size ,
- Morphological Measurements ,
- Variational Autoencoder ,
- Source Dataset ,
- Inception Distance ,
- Fréchet Inception Distance ,
- StyleGAN ,
- Physical Pixel Size ,
- Adversarial Neural Network ,
- Compressed Representation ,
- Physical Scale ,
- Average Power Spectrum ,
- Reconstruction Loss ,
- Kullback-Leibler ,
- Effective Radius ,
- Feature Extraction Network ,
- Color Distribution ,
- Residual Block ,
- Mean Square Error ,
- Background Noise ,
- Data Augmentation ,
- Weighting Factor ,
- Linear Interpolation ,
- Latent Representation ,
- Additional Channels ,
- Decrease In Loss ,
- Decrease In Error ,
- Latent Vector ,
- Wasserstein Distance ,
- Machine Learning Models ,
- Image Rotation ,
- Max Planck Society ,
- Morphological Parameters
- Author Keywords