论文标题
GL-GAN：图像生成的自适应全球和局部二元优化模型
GL-GAN: Adaptive Global and Local Bilevel Optimization model of Image Generation
论文作者
论文摘要
尽管生成的对抗网络在图像生成中表现出了显着的性能，但图像现实主义和收敛速度存在一些挑战。某些模型的结果显示出生成的图像中质量的不平衡，其中与其他区域相比，某些有缺陷的部分出现。与一般单一的全局优化方法不同，我们引入了自适应全局和局部二元优化模型（GL-GAN）。该模型以互补和促进的方式实现了高分辨率图像的生成，其中全球优化是为了优化整个图像，而本地仅是为了优化低质量领域。借助简单的网络结构，允许GL-GAN通过局部二线优化有效地避免不平衡的性质，这是通过首先定位低质量区域然后优化它们来实现的。此外，通过使用歧视器输出的特征映射提示，我们建议自适应本地和全局优化方法（ADA-OP）进行特定实现，并发现它提高了收敛速度。与当前的GAN方法相比，我们的模型在Celeba，Celeba-HQ和LSUN数据集上显示出令人印象深刻的性能。
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.
