arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02436cs.CVeess.IV
收藏

GL-GAN:自适应全局和局部双层优化图像生成模型

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

College of Informatics(信息学院);Huazhong Agricultural University(华中农业大学)

Ying Liu, Wenhong Cai, Xiaohui Yuan, Jinhai Xiang

摘要:

虽然生成对抗网络在图像生成方面表现出了卓越的性能,但在图像真实感和收敛速度方面存在一些挑战。一些模型的结果显示生成的图像内的质量的不平衡,其中与其他区域相比出现一些缺陷部分。与一般的单一全局优化方法不同,本文提出了一种自适应全局和局部双层优化模型(GL-GAN)。该模型以互补促进的方式实现了高分辨率图像的生成,全局优化是对图像整体的优化,局部优化只是对低质量区域的优化。通过简单的网络结构,GL-GAN可以有效地避免局部双层优化的不平衡性,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,通过使用特征映射的线索,我们提出了自适应局部和全局优化方法(Ada-OP)的具体实现,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数据集上表现出令人印象深刻的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑