Generative Modeling

Deep Generative Classifier with Short Run Inference

Deep generative classifier employs Short Run Markov Chain Monte Carlo inference with Langevin dynamics and backpropagation through time

Topology Adaptive Snakes Improve Mask Generation for Image Inpainting

T-snake deformable models, which can segment complex-shaped structures, improve generated masks passed to a GAN for image inpainting

Learning Multi-Layer Latent Variable Model with Short Run MCMC Inference Dynamics

Short Run MCMC sampling is utilized in a deep generative model with multiple layers of latent variables

Formulation of Variational Lower Bound and Application of VAE to MNIST Dataset

Formulation of the evidence lower bound (ELBO) for the variational autoencoder and an application to synthesizing binary images