The Catalogue for Galaxy Morphological Classification of the Legacy Surveys with Deformable Convolutional Neural Networks

The paper "Galaxy Morphological Classification of the Legacy Surveys with Deformable Convolutional NeuralNetworks" incorporate layer attention and deformable convolution into a convolutional neural network (CNN) to bolster its spatial feature and geometric transformation modeling capabilities. The proposed method was used to Data Release 9 of the Legacy Surveys, and present a galaxy morphological classification catalogue including approximately 71 million galaxies and the probability of each galaxy to be categorized as Round, In-between, Cigar-shaped, Edge-on, Spiral, Irregular and Error.