GMRF MCVAE embeds Gaussian Markov Random Fields into VAE prior and posterior distributions to explicitly model cross-component relationships, reporting SOTA results on a synthetic Copula dataset and improved coherence on BIKED.
Generative Models of Visually Grounded Imagination
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before. We call the ability to create images of novel semantic concepts visually grounded imagination. In this paper, we show how we can modify variational auto-encoders to perform this task. Our method uses a novel training objective, and a novel product-of-experts inference network, which can handle partially specified (abstract) concepts in a principled and efficient way. We also propose a set of easy-to-compute evaluation metrics that capture our intuitive notions of what it means to have good visual imagination, namely correctness, coverage, and compositionality (the 3 C's). Finally, we perform a detailed comparison of our method with two existing joint image-attribute VAE methods (the JMVAE method of Suzuki et.al. and the BiVCCA method of Wang et.al.) by applying them to two datasets: the MNIST-with-attributes dataset (which we introduce here), and the CelebA dataset.
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Component VAE with Gaussian Markov Random Field
GMRF MCVAE embeds Gaussian Markov Random Fields into VAE prior and posterior distributions to explicitly model cross-component relationships, reporting SOTA results on a synthetic Copula dataset and improved coherence on BIKED.