Diverse Image Generation via Self-Conditioned GANs
Diverse Image Generation via Self-Conditioned GANs
复制标题
DOI：
10.1109/cvpr42600.2020.01429
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Steven Liu;Tongzhou Wang;David Bau;Jun-Yan Zhu;A. Torralba
中科院分区：
文献类型：
--
作者：
Steven Liu;Tongzhou Wang;David Bau;Jun-Yan Zhu;A. Torralba
我们介绍了一种简单但有效的非监督生成各种图像的方法。我们训练了一个类条件GAN模型，而不使用人工标注的类标签。相反，我们的模型是有条件的，这些标签是从鉴别器的特征空间中自动聚类而来的。我们的集群步骤自动发现不同的模式，并显式地要求生成器覆盖它们。在标准模式崩溃基准测试上的实验表明，我们的方法在处理模式崩溃时的性能优于其他几种竞争方法。与以前的方法相比，我们的方法在ImageNet和Places365等大规模数据集上也表现良好，改善了多样性和标准度量(例如Fréchet初始距离)。
We introduce a simple but effective unsupervised method for generating diverse images. We train a class-conditional GAN model without using manually annotated class labels. Instead, our model is conditional on labels automatically derived from clustering in the discriminator’s feature space. Our clustering step automatically discovers diverse modes, and explicitly requires the generator to cover them. Experiments on standard mode collapse benchmarks show that our method outperforms several competing methods when addressing mode collapse. Our method also performs well on large-scale datasets such as ImageNet and Places365, improving both diversity and standard metrics (e.g., Fréchet Inception Distance), compared to previous methods.