Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we introduce a novel augmentation scheme designed specifically for GAN-based semantic image synthesis models. We propose to randomly warp object shapes in the semantic label maps used as an input to the generator. The local shape discrepancies between the warped and non-warped label maps and images enable the GAN to learn better the structural and geometric details of the scene and thus to improve the quality of generated images. While benchmarking the augmented GAN models against their vanilla counterparts, we discover that the quantification metrics reported in the previous semantic image synthesis studies are strongly biased towards specific semantic classes as they are derived via an external pre-trained segmentation network. We therefore propose to improve the established semantic image synthesis evaluation scheme by analyzing separately the performance of generated images on the biased and unbiased classes for the given segmentation network. Finally, we show strong quantitative and qualitative improvements obtained with our augmentation scheme, on both class splits, using state-of-the-art semantic image synthesis models across three different datasets. On average across COCO-Stuff, ADE20K and Cityscapes datasets, the augmented models outperform their vanilla counterparts by ~3 mIoU and ~10 FID points.


翻译:尽管数据增强是提升深层神经网络性能的一种事实上的技术,但很少注意为基因对抗网络(GANs)制定增强战略。为此,我们引入了专门为基于GAN的语义图像合成模型设计的新型增强计划。我们建议随机扭曲用于生成器的语义标签图中的物体形状;扭曲标签图和图象与非扭曲标签图和图象之间的局部形状差异使GAN能够更好地了解场景的结构和几何细节,从而提高生成图像的质量。在将增强的GAN模型与其香草类对应方进行基准化的同时,我们发现,先前的语义图像合成研究中所报告的量化指标非常偏向特定的语义类,因为它们是通过外部事先训练的分解网络衍生出来的。因此,我们提议通过不同比例的合成、州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-

0
下载
关闭预览

相关内容

Hierarchically Structured Meta-learning
CreateAMind
23+阅读 · 2019年5月22日
条件GAN重大改进!cGANs with Projection Discriminator
CreateAMind
8+阅读 · 2018年2月7日
已删除
将门创投
5+阅读 · 2017年8月15日
SwapText: Image Based Texts Transfer in Scenes
Arxiv
4+阅读 · 2020年3月18日
Using Scene Graph Context to Improve Image Generation
VIP会员
相关VIP内容
Top
微信扫码咨询专知VIP会员