Improving Variational Auto-Encoders using Householder Flow
Variational auto-encoders (VAE) are scalable and powerful generative models. However, the choice of the variational posterior determines tractability and flexibility of the VAE. Commonly, latent variables are modeled using the normal distribution with a diagonal covariance matrix. This results in computational efficiency but typically it is not flexible enough to match the true posterior distribution. One fashion of enriching the variational posterior distribution is application of normalizing flows, i.e., a series of invertible transformations to latent variables with a simple posterior. In this paper, we follow this line of thinking and propose a volume-preserving flow that uses a series of Householder transformations. We show empirically on MNIST dataset and histopathology data that the proposed flow allows to obtain more flexible variational posterior and competitive results comparing to other normalizing flows.
Code (2)
Tasks
Computational EfficiencyMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Topic-Guided Variational Autoencoders for Text Generation
We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our mo…
Conditional Text GenerationText GenerationOn the relationship between Normalising Flows and Variational- and Denoising Autoencoders
Normalising Flows (NFs) are a class of likelihood-based generative models that have recently gained popularity. They are based on the idea of transforming a simple density into that of the data. We seek to better underst…
DenoisingNormalising FlowsRepresentation LearningFew Shot Activity Recognition Using Variational Inference
There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of…
Action RecognitionActivity RecognitionFew-Shot LearningHuman Activity Recognition+1Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech
We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art seque…
DisentanglementExpressive Speech SynthesisSpeech Synthesistext-to-speech+2DoS and DDoS Mitigation Using Variational Autoencoders
DoS and DDoS attacks have been growing in size and number over the last decade and existing solutions to mitigate these attacks are in general inefficient. Compared to other types of malicious cyber attacks, DoS and DDoS…
Anomaly Detection