Latent Dirichlet Allocation in Generative Adversarial Networks

2018/12/17 by Lili Pan, Shen Cheng, Pan, Lili +7
Computer Science · Mathematics · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Music and Audio Processing #cs.CV #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1812.06571

openalex publication_date 2018/12/17 · arxiv created 2019/11/06 · arxiv updated 2019/11/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Auto-Encoding Variational Bayes
• Learning Multiple Layers of Features from Tiny Images

Related

• A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision
• Optimizing the Latent Space of Generative Networks
• Generalized Latent Variable Recovery for Generative Adversarial Networks
• Generative adversarial networks
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments