For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Iterative Adversarial Inference with Re-Inference Chain for Deep Graphical Models
Zhihao LIU Hui YIN Hua HUANG
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2019/08/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
deep graphical model, generative adversarial nets, latent variable, inference, generation,
Full Text: PDF(316.8KB)>>
Deep Graphical Model (DGM) based on Generative Adversarial Nets (GANs) has shown promise in image generation and latent variable inference. One of the typical models is the Iterative Adversarial Inference model (GibbsNet), which learns the joint distribution between the data and its latent variable. We present RGNet (Re-inference GibbsNet) which introduces a re-inference chain in GibbsNet to improve the quality of generated samples and inferred latent variables. RGNet consists of the generative, inference, and discriminative networks. An adversarial game is cast between the generative and inference networks and the discriminative network. The discriminative network is trained to distinguish between (i) the joint inference-latent/data-space pairs and re-inference-latent/data-space pairs and (ii) the joint sampled-latent/generated-data-space pairs. We show empirically that RGNet surpasses GibbsNet in the quality of inferred latent variables and achieves comparable performance on image generation and inpainting tasks.