Dual Contradistinctive Generative Autoencoder

Description

Summary

• We present a new generative autoencoder model with dual contradistinctive losses to improve generative autoencoder that performs simultaneous inference (reconstruction) and synthesis (sampling).
• However, the result of VAE/GAN is sub-optimal, as shown in Table 1.††* indicates equal contribution The pixel-wise reconstruction loss in the standard VAE [kingma2013auto] typically results in blurry images with degenerated semantics.
• VAE/GAN [VAEGAN] adopts an adversarial loss to improve the quality of the image, but its output for both reconstruction and synthesis (new samples) is still unsatisfactory.
• IntroVAE [huang2018introvae] adds a loop from the output back to the input and is able to attain image quality that is on par with some modern GANs in some aspects.