论文标题
汽车形象生成的深卷积剂量
Deep Convolutional GANs for Car Image Generation
论文作者
论文摘要
在本文中，我们调查了深卷积剂在汽车图像产生中的应用。我们通过实施Wasserstein损失来减少模式崩溃并在歧视者末尾引入辍学来提高常用的DCGAN架构，以引入随机性。此外，我们在发电机的末端引入卷积层，以提高表现力和光滑的噪声。 DCGAN架构上的所有这些改进都包括我们对新型布尔甘建筑的提议，该建筑能够将FID从195.922（基线）降低到165.966。
In this paper, we investigate the application of deep convolutional GANs on car image generation. We improve upon the commonly used DCGAN architecture by implementing Wasserstein loss to decrease mode collapse and introducing dropout at the end of the discrimiantor to introduce stochasticity. Furthermore, we introduce convolutional layers at the end of the generator to improve expressiveness and smooth noise. All of these improvements upon the DCGAN architecture comprise our proposal of the novel BoolGAN architecture, which is able to decrease the FID from 195.922 (baseline) to 165.966.
