Class-Distinct and Class-Mutual Image Generation with GANs

by   Takuhiro Kaneko, et al.

We describe a new problem called class-distinct and class-mutual (DM) image generation. Typically in class-conditional image generation, it is assumed that there are no intersections between classes, and a generative model is optimized to fit discrete class labels. However, in real-world scenarios, it is often required to handle data in which class boundaries are ambiguous or unclear. For example, data crawled from the web tend to contain mislabeled data resulting from confusion. Given such data, our goal is to construct a generative model that can be controlled for class specificity, which we employ to selectively generate class-distinct and class-mutual images in a controllable manner. To achieve this, we propose novel families of generative adversarial networks (GANs) called class-mixture GAN (CMGAN) and class-posterior GAN (CPGAN). In these new networks, we redesign the generator prior and the objective function in auxiliary classifier GAN (AC-GAN), then extend these to class-mixture and arbitrary class-overlapping settings. In addition to an analysis from an information theory perspective, we empirically demonstrate the effectiveness of our proposed models for various class-overlapping settings (including synthetic to real-world settings) and tasks (i.e., image generation and image-to-image translation).


page 5

page 17

page 19

page 20

page 21

page 22

page 23

page 24


DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion

Class-conditional image generation using generative adversarial networks...

RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis

Understanding three-dimensional (3D) geometries from two-dimensional (2D...

Conditional Image Generation with One-Vs-All Classifier

This paper explores conditional image generation with a One-Vs-All class...

Dual Projection Generative Adversarial Networks for Conditional Image Generation

Conditional Generative Adversarial Networks (cGANs) extend the standard ...

Intriguing Property of GAN for Remote Sensing Image Generation

Generative adversarial networks (GANs) have achieved remarkable progress...

TreeGAN: Incorporating Class Hierarchy into Image Generation

Conditional image generation (CIG) is a widely studied problem in comput...

Instance-Conditioned GAN

Generative Adversarial Networks (GANs) can generate near photo realistic...

Code Repositories


CP-GAN: Class-Distinct and Class-Mutual Image Generation with GANs

view repo

Please sign up or login with your details

Forgot password? Click here to reset