Extracting Semantic Knowledge from GANs with Unsupervised Learning

TL;DR

This paper introduces KLiSH, a clustering algorithm that exploits the linear separability of GAN features to extract fine-grained semantics, enabling unsupervised semantic segmentation and semantic-conditional image synthesis.

Contribution

It presents a novel clustering method, KLiSH, that effectively extracts semantics from GAN features, facilitating unsupervised downstream tasks without human annotations.

Findings

KLiSH successfully clusters GAN features across various datasets.

Enables training of semantic segmentation networks without labeled data.

Facilitates semantic-conditional image synthesis from GANs.

Abstract

Recently, unsupervised learning has made impressive progress on various tasks. Despite the dominance of discriminative models, increasing attention is drawn to representations learned by generative models and in particular, Generative Adversarial Networks (GANs). Previous works on the interpretation of GANs reveal that GANs encode semantics in feature maps in a linearly separable form. In this work, we further find that GAN's features can be well clustered with the linear separability assumption. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN's features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects, e.g., car, portrait, animals, and so on. With KLiSH, we can sample images from GANs along with their segmentation masks and synthesize paired image-segmentation datasets. Using the synthesized datasets, we enable two downstream applications. First, we train semantic segmentation networks on these datasets and test them on real images, realizing unsupervised semantic segmentation. Second, we train image-to-image translation networks on the synthesized datasets, enabling semantic-conditional image synthesis without human annotations.