Unsupervised learning of geometrical features from images by explicit group actions enforcementDownload PDF

26 Sept 2022, 12:09 (modified: 09 Nov 2022, 02:12)NeurReps 2022 PosterReaders: Everyone
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.
4 Replies

Loading