# Generative Adversarial Image Synthesis with Decision Tree Latent Controller

Source: [Generative Adversarial Image Synthesis with Decision Tree Latent Controller](<https://www.sota2.com/research/paper/68fa646d1e209131cea04a5f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:04:03.574Z

Authors: Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino

Published: 2018-05-27T10:56:02.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1805.10603>)

[PDF](<https://arxiv.org/pdf/1805.10603.pdf>)
