Deep Mixture Generative Autoencoders
By Fei Ye, Adrian G. Bors. 2021
37 citations recorded by the source corpus.
Variational autoencoders (VAEs) are one of the most popular unsupervised generative models that rely on learning latent representations of data. In this article, we extend the classical concept of Gaussian mixtures into the deep variational framework by proposing a mixture of VAEs (MVAE). Each component in the MVAE model is implemented by a variational encoder and has an associated subdecoder. The separation between the latent spaces modeled by different encoders is enforced using the $d$ -variable Hilbert–Schmidt independence criterion (dHSIC). Each component would capture different data variational features. We also propose a mechanism for finding the appropriate number of VAE components for a given task, leading to an optimal architecture. The differentiable categorical Gumbel-softmax distribution is used in order to generate dropout masking parameters within the end-to-end backpropagation training framework. Extensive experiments show that the proposed MVAE model can learn a rich latent data representation and is able to discover additional underlying data representation factors.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
In Signal Processing
Citations in the corpus
- Task-Free Continual Learning via Online Discrepancy Distance Learning (2022, neutral): “Due to its robust generation and inference mechanisms, VAEs have been widely used in many applications [48, 49, 50, 51, 54, 61].”
- Continual Variational Autoencoder Learning via Online Cooperative Memorization (2022, methodology): “We follow the settings from [61], as described in Appendix-H.”
- Learning an Evolved Mixture Model for Task-Free Continual Learning (2022, background): “Another approach for TFCL is based on the expansion of the network architecture or by adding new components to a mixture model [19, 20, 21].”
- Lifelong Generative Modelling Using Dynamic Expansion Graph Model (2021, methodology): “We also compare with LIMix (Ye and Bors 2021e) and implement CN-DPM (Lee et al. 2020) with the optimal setting, namely CN-DPM* (See details in Appendix-L.1 from SM1).”
- Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process (2021, methodology): “Each pθj (x | z) is implemented as a Gaussian distribution N (gθj (z),Σ) with Σ considered as a diagonal matrix, and gθj represents the deterministic mapping that maps z into the mean of pθj (x | z), implemented as a deep learning network [53, 54].”
- InfoVAEGAN: Learning Joint Interpretable Representations by Information Maximization and Maximum Likelihood (2021, background): “Learning disentangled representations that may capture semantic meaningful information can allow to explicitly edit images and is useful for a variety of tasks [1, 2, 3].”
- Lifelong Twin Generative Adversarial Networks (2021, methodology): “We enable the Student for learning dissentangled representations [18, 19] by penalizing the Kullback-Leibler divergence between the posterior and prior distributions, [20] :”