Latent Dirichlet Allocation in Generative Adversarial Networks
We study the problem of multimodal generative modelling of images based on generative adversarial networks (GANs). Despite the success of existing methods, they often ignore the underlying structure of vision data or its multimodal generation characteristics. To address this problem, we introduce the Dirichlet prior for multimodal image generation, which leads to a new Latent Dirichlet Allocation based GAN (LDAGAN). In detail, for the generative process modelling, LDAGAN defines a generative mode for each sample, determining which generative sub-process it belongs to. For the adversarial training, LDAGAN derives a variational expectation-maximization (VEM) algorithm to estimate model parameters. Experimental results on real-world datasets have demonstrated the outstanding performance of LDAGAN over other existing GANs.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Generationmultimodal generationStochastic OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Vectorized Bayesian Inference for Latent Dirichlet-Tree Allocation
Latent Dirichlet Allocation (LDA) is a foundational model for discovering latent thematic structure in discrete data, but its Dirichlet prior cannot represent the rich correlations and hierarchical relationships often pr…
Computational EfficiencyBayesian InferenceGaussian Hierarchical Latent Dirichlet Allocation: Bringing Polysemy Back
Topic models are widely used to discover the latent representation of a set of documents. The two canonical models are latent Dirichlet allocation, and Gaussian latent Dirichlet allocation, where the former uses multinom…
Topic ModelsAnalysis of Variational Bayesian Latent Dirichlet Allocation: Weaker Sparsity Than MAP
Latent Dirichlet allocation (LDA) is a popular generative model of various objects such as texts and images, where an object is expressed as a mixture of latent topics. In this paper, we theoretically investigate variati…
Hyperspectral Unmixing with Endmember Variability using Semi-supervised Partial Membership Latent Dirichlet Allocation
A semi-supervised Partial Membership Latent Dirichlet Allocation approach is developed for hyperspectral unmixing and endmember estimation while accounting for spectral variability and spatial information. Partial Member…
Hyperspectral UnmixingSpatial Latent Dirichlet Allocation
In recent years, the language model Latent Dirichlet Allocation (LDA), which clusters co-occurring words into topics, has been widely appled in the computer vision field. However, many of these applications have difficul…
Language ModelingLanguage Modelling