DeepAI AI Chat
Log In Sign Up

Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs

by   Nicholas Watters, et al.

We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-"coordinate" channels, and apply a fully convolutional network with 1x1 stride. This provides an architectural prior for dissociating positional from non-positional features in the latent distribution of VAEs, yet without providing any explicit supervision to this effect. We show that this architecture, which we term the Spatial Broadcast decoder, improves disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a particularly dramatic benefit when applied to datasets with small objects. We also emphasize a method for visualizing learned latent spaces that helped us diagnose our models and may prove useful for others aiming to assess data representations. Finally, we show the Spatial Broadcast Decoder is complementary to state-of-the-art (SOTA) disentangling techniques and when incorporated improves their performance.


Consensus Capacity of Noisy Broadcast Channels

We study communication with consensus over a broadcast channel - the rec...

Variational Tracking and Prediction with Generative Disentangled State-Space Models

We address tracking and prediction of multiple moving objects in visual ...

Deep disentangled representations for volumetric reconstruction

We introduce a convolutional neural network for inferring a compact dise...

Variance Constrained Autoencoding

Recent state-of-the-art autoencoder based generative models have an enco...

Data Overlap: A Prerequisite For Disentanglement

Learning disentangled representations with variational autoencoders (VAE...

How do Variational Autoencoders Learn? Insights from Representational Similarity

The ability of Variational Autoencoders (VAEs) to learn disentangled rep...