Generative Adversarial Image Synthesis with Decision Tree Latent Controller

05/27/2018
by   Takuhiro Kaneko, et al.
0

This paper proposes the decision tree latent controller generative adversarial network (DTLC-GAN), an extension of a GAN that can learn hierarchically interpretable representations without relying on detailed supervision. To impose a hierarchical inclusion structure on latent variables, we incorporate a new architecture called the DTLC into the generator input. The DTLC has a multiple-layer tree structure in which the ON or OFF of the child node codes is controlled by the parent node codes. By using this architecture hierarchically, we can obtain the latent space in which the lower layer codes are selectively used depending on the higher layer ones. To make the latent codes capture salient semantic features of images in a hierarchically disentangled manner in the DTLC, we also propose a hierarchical conditional mutual information regularization and optimize it with a newly defined curriculum learning method that we propose as well. This makes it possible to discover hierarchically interpretable representations in a layer-by-layer manner on the basis of information gain by only using a single DTLC-GAN model. We evaluated the DTLC-GAN on various datasets, i.e., MNIST, CIFAR-10, Tiny ImageNet, 3D Faces, and CelebA, and confirmed that the DTLC-GAN can learn hierarchically interpretable representations with either unsupervised or weakly supervised settings. Furthermore, we applied the DTLC-GAN to image-retrieval tasks and showed its effectiveness in representation learning.

READ FULL TEXT

page 1

page 2

page 6

page 7

page 9

page 14

page 27

page 29

research
06/12/2016

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

This paper describes InfoGAN, an information-theoretic extension to the ...
research
07/09/2021

InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood

Learning disentangled and interpretable representations is an important ...
research
07/14/2017

Guiding InfoGAN with Semi-Supervision

In this paper we propose a new semi-supervised GAN architecture (ss-Info...
research
11/21/2016

Temporal Generative Adversarial Nets with Singular Value Clipping

In this paper, we propose a generative model, Temporal Generative Advers...
research
04/26/2021

EigenGAN: Layer-Wise Eigen-Learning for GANs

Recent studies on Generative Adversarial Network (GAN) reveal that diffe...
research
05/02/2015

Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models

Deep learning has shown state-of-art classification performance on datas...

Please sign up or login with your details

Forgot password? Click here to reset