Unsupervised learning of geometrical features from images by explicit group actions enforcement

Francesco Calisto, Luca Bottero, Valerio Pagliarino

Keywords: autoencoders, group actions, geometric priors, latent space disentanglement

TL;DR: In this work we propose an autoencoder architecture capable of automatically learning meaningful geometric features of objects in images, achieving a disentangled representation of 2D objects

Abstract: In this work we propose an autoencoder architecture capable of automatically learning meaningful geometric features of objects in images, achieving a disentangled representation of 2D objects. It is made of a standard dense autoencoder that captures the deep features identifying the shapes and an additional encoder that extracts geometric latent variables regressed in an unsupervised manner. These are then used to apply a transformation on the output of the deep features decoder. The promising results show that this approach performs better than a non-constrained model having more degrees of freedom.