DES to HSC: Detecting low surface brightness galaxies in the Abell 194 cluster using transfer learning

Low surface brightness galaxies (LSBGs) are important for understanding galaxy evolution and cosmological models. The upcoming large-scale surveys are expected to uncover a large number of LSBGs, requiring accurate automated or machine learning-based methods for their detection. We study the scope of transfer learning for the identification of LSBGs. We use transformer models divided into two categories: LSBG Detection Transformer (LSBG DETR) and LSBG Vision Transformer (LSBG ViT), trained on Dark Energy Survey (DES) data, to identify LSBGs from dedicated Hyper Suprime-Cam (HSC) observations of the Abell 194 cluster, which are two magnitudes deeper than DES. The data from DES and HSC were standardized based on pixel-level surface brightness. We used two transformer ensembles to detect LSBGs. This was followed by a single-component Sérsic model fit and a final visual inspection to filter out potential false positives and improve sample purity. We present a sample of 171 low surface brightness galaxies (LSBGs) in the Abell 194 cluster using HSC data, including 87 new discoveries. Of these, 159 were identified using transformer models, and 12 additional LSBGs were found through visual inspection. The transformer model achieved a true positive rate (TPR) of 93% in HSC data without any fine-tuning. Among the LSBGs, 28 were classified as ultra-diffuse galaxies (UDGs). The number of UDGs and the radial UDG number density suggest a linear relationship between UDG numbers and cluster mass on a log scale. UDGs share similar Sérsic parameters with dwarf galaxies and occupy the extended end of the $R_{\mathrm{eff}}-M_g$ plane, suggesting they might be an extended subpopulation of dwarf galaxies. We have demonstrated that transformer models trained on shallower surveys can be successfully applied to deeper surveys with appropriate data normalization.