Learning Latent Subspaces in Variational Autoencoders
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a VAE-based generative model which we show is capable of extracting features correlated to binary labels in the data and structuring it in a latent subspace which is easy to interpret. Our model, the Conditional Subspace VAE (CSVAE), uses mutual information minimization to learn a low-dimensional latent subspace associated with each label that can easily be inspected and independently manipulated. We demonstrate the utility of the learned representations for attribute manipulation tasks on both the Toronto Face and CelebA datasets.
Code (1)
Tasks
AttributeMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
IntroVAC: Introspective Variational Classifiers for Learning Interpretable Latent Subspaces
Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they pro…
DecoderLatent Space Characterization of Autoencoder Variants
Understanding the latent spaces learned by deep learning models is crucial in exploring how they represent and generate complex data. Autoencoders (AEs) have played a key role in the area of representation learning, with…
DenoisingRepresentation LearningVariational decomposition autoencoding improves disentanglement of latent representations
Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the abil…
Representation LearningSpeech RecognitionLearning Weighted Submanifolds with Variational Autoencoders and Riemannian Variational Autoencoders
Manifold-valued data naturally arises in medical imaging. In cognitive neuroscience, for instance, brain connectomes base the analysis of coactivation patterns between different brain regions on the analysis of the corre…
Riemannian optimizationTime Series AnalysisDIVA: Domain Invariant Variational Autoencoders
We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain. We propose the Domain Invariant Variational…
Domain GeneralizationRotated MNIST