GLSR-VAE: Geodesic Latent Space Regularization for Variational AutoEncoder Architectures
VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we would like to take into account at generation time. We propose in this paper GLSR-VAE, a Geodesic Latent Space Regularization for the Variational AutoEncoder architecture and its generalizations which allows a fine control on the embedding of the data into the latent space. When augmenting the VAE loss with this regularization, changes in the learned latent space reflects changes of the attributes of the data. This deeper understanding of the VAE latent space structure offers the possibility to modulate the attributes of the generated data in a continuous way. We demonstrate its efficiency on a monophonic music generation task where we manage to generate variations of discrete sequences in an intended and playful way.
Code (0)
등록된 구현이 없습니다.
Tasks
Music GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VTAE: Variational Transformer Autoencoder with Manifolds Learning
Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables and these models use a nonlinear function (generator) to map latent samples …
Representation LearningEnforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation
Latent space interpolations are a powerful tool for navigating deep generative models in applied settings. An example is single-cell RNA sequencing, where existing methods model cellular state transitions as latent space…
Geodesic Clustering in Deep Generative Models
Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data. These representations, however, tend to much distort relationships between points, i.e. p…
ClusteringEncoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations
While variational autoencoders have been successful in several tasks, the use of conventional priors are limited in their ability to encode the underlying structure of input data. We introduce an Encoded Prior Sliced Was…
Interpretable Representation Learning of Cardiac MRI via Attribute Regularization
Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. Several approaches have been recently considered to encode attributes in the latent spac…
AttributeRepresentation Learning