Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces

Understand

Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information.

• For example, variational autoencoders with autoregressive decoders often collapse into autodecoders, where they learn to ignore the encoder input.
• In this work, we demonstrate that adding an auxiliary decoder to regularize the latent space can prevent this collapse, but successful auxiliary decoding tasks are domain dependent.
• Auxiliary decoders can increase the amount of semantic information encoded in the latent space and visible in the reconstructions.