Hierarchical Multimodal Variational Autoencoders
Humans find structure in natural phenomena by absorbing stimuli from multiple input sources such as vision, text, and speech. We study the use of deep generative models that generate multimodal data from latent representations. Existing approaches generate samples using a single shared latent variable, sometimes with marginally independent latent variables to capture modality-specific variations. However, there are cases where modality-specific variations depend on the kind of structure shared across modalities. To capture such heterogeneity, we propose a hierarchical multimodal VAE (HMVAE) that represents modality-specific variations using latent variables dependent on a shared top-level variable. Our experiments on the CUB and the Oxford Flower datasets show that the HMVAE can represent multimodal heterogeneity and outperform existing methods in sample generation quality and quantitative measures as the held-out log-likelihood.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hierarchical Bayes Autoencoders
Autoencoders are powerful generative models for complex data, such as images. However, standard models like the variational autoencoder (VAE) typically have unimodal Gaussian decoders, which cannot effectively represent …
DecoderVariational InferenceVariational Composite Autoencoders
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable. Previous variational autoencoders can be low effective due to the straightforward enc…
DecoderCoVAE: correlated multimodal generative modeling
Multimodal Variational Autoencoders have emerged as a popular tool to extract effective representations from rich multimodal data. However, such models rely on fusion strategies in latent space that destroy the joint sta…
Discouraging posterior collapse in hierarchical Variational Autoencoders using context
Hierarchical Variational Autoencoders (VAEs) are among the most popular likelihood-based generative models. There is a consensus that the top-down hierarchical VAEs allow effective learning of deep latent structures and …
Learning variational autoencoders via MCMC speed measures
Variational autoencoders (VAEs) are popular likelihood-based generative models which can be efficiently trained by maximizing an Evidence Lower Bound (ELBO). There has been much progress in improving the expressiveness o…