5 papers
A Contrastive Learning Approach for Training Variational Autoencoder Priors
Jyoti Aneja, Alexander Schwing, Jan Kautz +1
Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in many domains. However, they struggle to generate high-quality images…
VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
Zhisheng Xiao, Karsten Kreis, Jan Kautz +1
Energy-based models (EBMs) have recently been successful in representing complex distributions of small images. However, sampling from them requires expensive Markov chain Monte Ca…
NVAE: A Deep Hierarchical Variational Autoencoder
Arash Vahdat, Jan Kautz
Normalizing flows, autoregressive models, variational autoencoders (VAEs), and deep energy-based models are among competing likelihood-based frameworks for deep generative learning…
Contrastive Learning for Weakly Supervised Phrase Grounding
Tanmay Gupta, Arash Vahdat, Gal Chechik +3
Phrase grounding, the problem of associating image regions to caption words, is a crucial component of vision-language tasks. We show that phrase grounding can be learned by optimi…
UNAS: Differentiable Architecture Search Meets Reinforcement Learning
Arash Vahdat, Arun Mallya, Ming-Yu Liu +1
Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demons…