Structured Generative Adversarial Networks

11/02/2017
by   Zhijie Deng, et al.
0

We study the problem of conditional generative modeling based on designated semantics or structures. Existing models that build conditional generators either require massive labeled instances as supervision or are unable to accurately control the semantics of generated samples. We propose structured generative adversarial networks (SGANs) for semi-supervised conditional generative modeling. SGAN assumes the data x is generated conditioned on two independent latent variables: y that encodes the designated semantics, and z that contains other factors of variation. To ensure disentangled semantics in y and z, SGAN builds two collaborative games in the hidden space to minimize the reconstruction error of y and z, respectively. Training SGAN also involves solving two adversarial games that have their equilibrium concentrating at the true joint data distributions p(x, z) and p(x, y), avoiding distributing the probability mass diffusely over data space that MLE-based methods may suffer. We assess SGAN by evaluating its trained networks, and its performance on downstream tasks. We show that SGAN delivers a highly controllable generator, and disentangled representations; it also establishes start-of-the-art results across multiple datasets when applied for semi-supervised image classification (1.27 and 4000 labels, respectively). Benefiting from the separate modeling of y and z, SGAN can generate images with high visual quality and strictly following the designated semantic, and can be extended to a wide spectrum of applications, such as style transfer.

READ FULL TEXT

page 8

page 9

page 12

page 13

page 14

research
12/20/2019

Triple Generative Adversarial Networks

Generative adversarial networks (GANs) have shown promise in image gener...
research
07/14/2017

Guiding InfoGAN with Semi-Supervision

In this paper we propose a new semi-supervised GAN architecture (ss-Info...
research
12/12/2018

A Style-Based Generator Architecture for Generative Adversarial Networks

We propose an alternative generator architecture for generative adversar...
research
09/19/2017

Triangle Generative Adversarial Networks

A Triangle Generative Adversarial Network (Δ-GAN) is developed for semi-...
research
06/19/2023

Probabilistic matching of real and generated data statistics in generative adversarial networks

Generative adversarial networks constitute a powerful approach to genera...
research
10/02/2018

Semi-supervised Text Regression with Conditional Generative Adversarial Networks

Enormous online textual information provides intriguing opportunities fo...
research
08/03/2020

The pursuit of beauty: Converting image labels to meaningful vectors

A challenge of the computer vision community is to understand the semant...

Please sign up or login with your details

Forgot password? Click here to reset