M^2VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood

03/18/2019

∙

This work gives an in-depth derivation of the trainable evidence lower bound obtained from the marginal joint log-Likelihood with the goal of training a Multi-Modal Variational Autoencoder (M^2VAE).

READ FULL TEXT

M^2VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood

A Perceived Environment Design using a Multi-Modal Variational Autoencoder for learning Active-Sensing

Multi-modal data generation with a deep metric variational autoencoder

FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion

Hierarchical Sparse Variational Autoencoder for Text Encoding

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

Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

M^2VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood

Related Research

A Perceived Environment Design using a Multi-Modal Variational Autoencoder for learning Active-Sensing

Multi-modal data generation with a deep metric variational autoencoder

FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion

Hierarchical Sparse Variational Autoencoder for Text Encoding

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

Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning

Embrace the Gap: VAEs Perform Independent Mechanism Analysis