Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed. Latent semantics discovered by unsupervised methods are relatively less disentangled than supervised methods since they do not use pre-trained attribute classifiers. We propose Scale Ranking Estimator (SRE), which is trained using self-supervision. SRE enhances the disentanglement in directions obtained by existing unsupervised disentanglement techniques. These directions are updated to preserve the ordering of variation within each direction in latent space. Qualitative and quantitative evaluation of the discovered directions demonstrates that our proposed method significantly improves disentanglement in various datasets. We also show that the learned SRE can be used to perform Attribute-based image retrieval task without further training.
翻译:提出了在经过事先训练的GANs潜在空间中发现可解释方向的几种方法。通过未经监督的方法发现的边端语义与监督的方法相比,相对较少分解,因为它们不使用经过事先训练的属性分类器。我们建议使用自我监督的自我监督培训的Scale 分级模拟器(SRE),SRE使现有的未经监督的分解技术获得的方向更加分解。这些方向得到更新,以保持隐蔽空间中每个方向内的变化顺序。对所发现方向的定性和定量评估表明,我们拟议的方法大大改进了各种数据集中的分解。我们还表明,所学的SRE可以在不经过进一步培训的情况下用于执行基于属性的图像检索任务。