DeepAI AI Chat
Log In Sign Up

Guided Variational Autoencoder for Disentanglement Learning

by   Zheng Ding, et al.

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.


page 4

page 5

page 6

page 7

page 8


Epitomic Variational Graph Autoencoder

Variational autoencoder (VAE) is a widely used generative model for unsu...

Variational Autoencoders Pursue PCA Directions (by Accident)

The Variational Autoencoder (VAE) is a powerful architecture capable of ...

Learning Robust Latent Representations for Controllable Speech Synthesis

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentang...

Category-Learning with Context-Augmented Autoencoder

Finding an interpretable non-redundant representation of real-world data...

GroupifyVAE: from Group-based Definition to VAE-based Unsupervised Representation Disentanglement

The key idea of the state-of-the-art VAE-based unsupervised representati...

Quaternion-Valued Variational Autoencoder

Deep probabilistic generative models have achieved incredible success in...

Polyline Based Generative Navigable Space Segmentation for Autonomous Visual Navigation

Detecting navigable space is a fundamental capability for mobile robots ...