GL-GAN: Adaptive Global and Local Bilevel Optimization model of Image Generation

TL;DR

GL-GAN introduces an adaptive global and local bilevel optimization framework that enhances image realism and convergence speed in high-resolution image generation by focusing on low-quality regions.

Contribution

The paper proposes a novel adaptive bilevel optimization model for GANs that effectively addresses image quality imbalance and accelerates convergence.

Findings

Improved image quality on CelebA, CelebA-HQ, and LSUN datasets.

Enhanced convergence speed using the Ada-OP method.

Effective avoidance of quality imbalance through local bilevel optimization.

Abstract

Although Generative Adversarial Networks have shown remarkable performance in image generation, there are some challenges in image realism and convergence speed. The results of some models display the imbalances of quality within a generated image, in which some defective parts appear compared with other regions. Different from general single global optimization methods, we introduce an adaptive global and local bilevel optimization model(GL-GAN). The model achieves the generation of high-resolution images in a complementary and promoting way, where global optimization is to optimize the whole images and local is only to optimize the low-quality areas. With a simple network structure, GL-GAN is allowed to effectively avoid the nature of imbalance by local bilevel optimization, which is accomplished by first locating low-quality areas and then optimizing them. Moreover, by using feature map cues from discriminator output, we propose the adaptive local and global optimization method(Ada-OP) for specific implementation and find that it boosts the convergence speed. Compared with the current GAN methods, our model has shown impressive performance on CelebA, CelebA-HQ and LSUN datasets.