Morphological classification of radio galaxies with Wasserstein generative adversarial network-supported augmentation
Standard
Morphological classification of radio galaxies with Wasserstein generative adversarial network-supported augmentation. / Rustige, Lennart; Kummer, Janis; Griese, Florian; Borras, Kerstin; Brüggen, Marcus; Connor, Patrick; Gaede, Frank; Kasiecka, Gregor; Knopp, Tobias; Schleper, Peter.
In: RAS Techniques and Instruments, Vol. 2, No. 1, 26.05.2023, p. 264–277.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Morphological classification of radio galaxies with Wasserstein generative adversarial network-supported augmentation
AU - Rustige, Lennart
AU - Kummer, Janis
AU - Griese, Florian
AU - Borras, Kerstin
AU - Brüggen, Marcus
AU - Connor, Patrick
AU - Gaede, Frank
AU - Kasiecka, Gregor
AU - Knopp, Tobias
AU - Schleper, Peter
PY - 2023/5/26
Y1 - 2023/5/26
N2 - Machine learning techniques that perform morphological classification of astronomical sources often suffer from a scarcity of labelled training data. Here, we focus on the case of supervised deep learning models for the morphological classification of radio galaxies, which is particularly topical for the forthcoming large radio surveys. We demonstrate the use of generative models, specifically Wasserstein generative adversarial networks (wGANs), to generate data for different classes of radio galaxies. Further, we study the impact of augmenting the training data with images from our wGAN on three different classification architectures. We find that this technique makes it possible to improve models for the morphological classification of radio galaxies. A simple fully connected neural network benefits most from including generated images into the training set, with a considerable improvement of its classification accuracy. In addition, we find it is more difficult to improve complex classifiers. The classification performance of a convolutional neural network can be improved slightly. However, this is not the case for a vision transformer.
AB - Machine learning techniques that perform morphological classification of astronomical sources often suffer from a scarcity of labelled training data. Here, we focus on the case of supervised deep learning models for the morphological classification of radio galaxies, which is particularly topical for the forthcoming large radio surveys. We demonstrate the use of generative models, specifically Wasserstein generative adversarial networks (wGANs), to generate data for different classes of radio galaxies. Further, we study the impact of augmenting the training data with images from our wGAN on three different classification architectures. We find that this technique makes it possible to improve models for the morphological classification of radio galaxies. A simple fully connected neural network benefits most from including generated images into the training set, with a considerable improvement of its classification accuracy. In addition, we find it is more difficult to improve complex classifiers. The classification performance of a convolutional neural network can be improved slightly. However, this is not the case for a vision transformer.
U2 - 10.1093/rasti/rzad016
DO - 10.1093/rasti/rzad016
M3 - SCORING: Journal article
VL - 2
SP - 264
EP - 277
IS - 1
ER -