论文标题
搜索有条件的生成对抗网络，搜索班级感知的发电机
Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks
论文作者
论文摘要
有条件的生成对抗网络（CGAN）旨在根据所提供的条件（例如\ eg，类级分布）生成图像。但是，现有方法对所有类都使用了相同的生成体系结构。本文提出了一个新颖的想法，该想法采用NAS来找到每个班级的独特架构。搜索空间包含常规和班级调制的卷积，后者旨在引入特定于类的信息，同时避免减少每个类生成器的培训数据。搜索算法遵循具有混合体系结构优化的重量分担管道，因此搜索成本不会随着类的数量而增长。为了了解采样策略，马尔可夫决策过程嵌入到搜索算法中，并应用了移动平均值以提高稳定性。我们在CIFAR10和CIFAR100上评估了我们的方法。除了在FID分数方面达到更好的图像生成质量外，我们还发现了一些有助于设计CGAN模型的见解。代码可从https://github.com/peterouzh/nas_cgan获得。
Conditional Generative Adversarial Networks (cGAN) were designed to generate images based on the provided conditions, \eg, class-level distributions. However, existing methods have used the same generating architecture for all classes. This paper presents a novel idea that adopts NAS to find a distinct architecture for each class. The search space contains regular and class-modulated convolutions, where the latter is designed to introduce class-specific information while avoiding the reduction of training data for each class generator. The search algorithm follows a weight-sharing pipeline with mixed-architecture optimization so that the search cost does not grow with the number of classes. To learn the sampling policy, a Markov decision process is embedded into the search algorithm and a moving average is applied for better stability. We evaluate our approach on CIFAR10 and CIFAR100. Besides achieving better image generation quality in terms of FID scores, we discover several insights that are helpful in designing cGAN models. Code is available at https://github.com/PeterouZh/NAS_cGAN.
