Despite the remarkable progress in Generative Adversarial Networks (GANs), unsupervised models fail to generalize to diverse datasets, such as ImageNet or Places365. To tackle such datasets, we rely on class-conditional GANs, which require class labels to train. These labels are often not available or are expensive to obtain.
We propose to increase unsupervised GAN quality by inferring class labels in a fully unsupervised manner. By periodically clustering already present discriminator features, we improve generation quality on large-scale datasets such as ImageNet and Places365. Besides increasing generation quality, we also automatically infer semantically meaningful clusters.
Don't forget to tag @stevliu in your comment, otherwise they may not be notified.