
This paper proposes a new variational bound that can tightly approximate the multi-modal data log-likelihood, and develops more flexible aggregation schemes based on permutation-invariant neural networks to encode latent variables from different modality subsets.


coremsg

learning-flexible-multi-modal-generative-models-with-permutation-invariant-encoders-and-tighter-variational-bounds


Learning Flexible Multi-Modal Generative Models with Permutation-Invariant Encoders and Tighter Variational Bounds
