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.

[1]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[2]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[3]  Yi Yang,et al.  GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data , 2017, BMVC 2017.

[4]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[5]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[6]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[7]  Jinwen Ma,et al.  DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images , 2017, ICLR.

[8]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[9]  David Vázquez,et al.  PixelVAE: A Latent Variable Model for Natural Images , 2016, ICLR.

[10]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[12]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[13]  Yann LeCun,et al.  Disentangling factors of variation in deep representation using adversarial training , 2016, NIPS.

[14]  Anil A. Bharath,et al.  Conditional Autoencoders with Adversarial Information Factorization , 2017, ArXiv.

[15]  Max Welling,et al.  The Variational Fair Autoencoder , 2015, ICLR.

[16]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[17]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[18]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[19]  Guillaume Lample,et al.  Fader Networks: Manipulating Images by Sliding Attributes , 2017, NIPS.

[20]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[21]  Jinwen Ma,et al.  ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes , 2018, ECCV.

[22]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[23]  Antonia Creswell,et al.  Adversarial Information Factorization , 2018 .

[24]  Amos J. Storkey,et al.  Censoring Representations with an Adversary , 2015, ICLR.

[25]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[26]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.