Flipped-Adversarial AutoEncoders
This work addresses the challenge of improving image reconstruction and latent representation in autoencoders for machine learning applications, though it appears incremental as it builds on existing hybrid adversarial-autoencoder methods.
The paper tackles the problem of training generative models and encoders simultaneously by proposing a flipped-Adversarial AutoEncoder (FAAE), which minimizes re-encoding errors in latent space and uses adversarial training in data space, resulting in sharper reconstructed images and rich semantic representations.
We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously trains a generative model G that maps an arbitrary latent code distribution to a data distribution and an encoder E that embodies an "inverse mapping" that encodes a data sample into a latent code vector. Unlike previous hybrid approaches that leverage adversarial training criterion in constructing autoencoders, FAAE minimizes re-encoding errors in the latent space and exploits adversarial criterion in the data space. Experimental evaluations demonstrate that the proposed framework produces sharper reconstructed images while at the same time enabling inference that captures rich semantic representation of data.