Guided Variational Autoencoder for Disentanglement Learning
arXiv:2004.01255
Abstract
We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. The learning objective is achieved by providing signals to the latent encoding/embedding in VAE without changing its main backbone architecture, hence retaining the desirable properties of the VAE. We design an unsupervised strategy and a supervised strategy in Guided-VAE and observe enhanced modeling and controlling capability over the vanilla VAE. In the unsupervised strategy, we guide the VAE learning by introducing a lightweight decoder that learns latent geometric transformation and principal components; in the supervised strategy, we use an adversarial excitation and inhibition mechanism to encourage the disentanglement of the latent variables. Guided-VAE enjoys its transparency and simplicity for the general representation learning task, as well as disentanglement learning. On a number of experiments for representation learning, improved synthesis/sampling, better disentanglement for classification, and reduced classification errors in meta-learning have been observed.
Accepted to CVPR 2020
References in corpus (13)
- Auto-Encoding Variational Bayes
- mixup: Beyond Empirical Risk Minimization
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Deeply-Supervised Nets
- Disentangling by Factorising
- Disentangling factors of variation in deep representations using adversarial training
- Optimizing the Latent Space of Generative Networks
- Flexibly Fair Representation Learning by Disentanglement
- DIVA: Domain Invariant Variational Autoencoders
- Learning Controllable Fair Representations
- Challenges in Disentangling Independent Factors of Variation
- BRUNO: A Deep Recurrent Model for Exchangeable Data