论文标题
Matchinggan：基于匹配的几张图像生成
MatchingGAN: Matching-based Few-shot Image Generation
论文作者
论文摘要
要为给定类别生成新图像，大多数深层生成模型都需要该类别的丰富培训图像，这些培训图像通常太贵了，无法获取。为了仅基于几个图像来实现生成的目标，我们建议使用基于匹配的生成对抗网络（GAN），以进行几个发射的生成，其中包括匹配的生成器和匹配的歧视器。匹配发电机可以将随机向量与来自同一类别的一些条件图像匹配，并根据融合功能为此类别生成新图像。匹配的判别器通过将生成图像的特征与条件图像的融合功能匹配，从而扩展了常规的GAN鉴别器。在三个数据集上进行的广泛实验证明了我们提出的方法的有效性。
To generate new images for a given category, most deep generative models require abundant training images from this category, which are often too expensive to acquire. To achieve the goal of generation based on only a few images, we propose matching-based Generative Adversarial Network (GAN) for few-shot generation, which includes a matching generator and a matching discriminator. Matching generator can match random vectors with a few conditional images from the same category and generate new images for this category based on the fused features. The matching discriminator extends conventional GAN discriminator by matching the feature of generated image with the fused feature of conditional images. Extensive experiments on three datasets demonstrate the effectiveness of our proposed method.
