crVAE-GAN (Channel-Recurrent Variational Autoencoder-Generative Adversarial Network) refers to a specific generative model designed to overcome limitations in capturing complex image types. It leverages recurrent connections, adversarial training, and novel regularizations to improve the generation of diverse and high-resolution images with interpretable latent representations.

Posts

Channel-Recurrent Autoencoding for Image Modeling

/in /by

Despite recent successes in synthesizing faces and bedrooms, existing generative models struggle to capture more complex image types (Figure 1), potentially due to the oversimplification of their latent space constructions. To tackle this issue, building on Variational Autoencoders (VAEs), we integrate recurrent connections across channels to both inference and generation steps, allowing the high-level features to be captured in global-to-local, coarse-to-fine manners. Combined with adversarial loss, our channel-recurrent VAE-GAN (crVAE-GAN) outperforms VAE-GAN in generating a diverse spectrum of high resolution images while maintaining the same level of computational efficacy. Our model produces interpretable and expressive latent representations to benefit downstream tasks such as image completion. Moreover, we propose two novel regularizations, namely the KL objective weighting scheme over time steps and mutual information maximization between transformed latent variables and the outputs, to enhance the training.

Read more