Yuksel, Oguz KaanSimsar, EnisEr, Ezgi GulperiYanardag, Pinar2022-07-042022-07-042022-07-042021-01-0110.1109/ICCV48922.2021.01400https://infoscience.epfl.ch/handle/20.500.14299/188924WOS:000798743204044Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of semantic editing operations, such as zoom or rotation. The discovery of such directions is often done in a supervised or semi-supervised manner and requires manual annotations which limits their use in practice. In comparison, unsupervised discovery allows finding subtle directions that are difficult to detect a priori. In this work, we propose a contrastive learning-based approach to discover semantic directions in the latent space of pre-trained GANs in a selfsupervised manner. Our approach finds semantically meaningful dimensions compatible with state-of-the-art methods.Computer Science, Artificial IntelligenceComputer Science, Theory & MethodsComputer Sciencetext::conference output::conference proceedings::conference paper