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

Understand

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.