From the intuitive notion of disentanglement, the image variations corresponding to different factors should be distinct from each other, and the disentangled representation should reflect those variations with separate dimensions. To discover the factors and learn disentangled representation, previous methods typically leverage an extra regularization term when learning to generate realistic images. However, the term usually results in a trade-off between disentanglement and generation quality. For the generative models pretrained without any disentanglement term, the generated images show semantically meaningful variations when traversing along different directions in the latent space. Based on this observation, we argue that it is possible to mitigate the trade-off by $(i)$ leveraging the pretrained generative models with high generation quality, $(ii)$ focusing on discovering the traversal directions as factors for disentangled representation learning. To achieve this, we propose Disentaglement via Contrast (DisCo) as a framework to model the variations based on the target disentangled representations, and contrast the variations to jointly discover disentangled directions and learn disentangled representations. DisCo achieves the state-of-the-art disentangled representation learning and distinct direction discovering, given pretrained non-disentangled generative models including GAN, VAE, and Flow. Source code is at https://github.com/xrenaa/DisCo.
翻译:从分解的直觉概念看,不同因素的图像变异应彼此区别,而分解的表达方式应分别反映这些变异。为了发现各种因素并学习分解的表达方式,以往的方法通常在学习产生现实的图像时利用一个额外的正规化术语。然而,该术语通常导致分解和生成质量之间的权衡。对于未经过任何分解术语的基因化模型而言,生成的图像显示沿着潜在空间不同方向穿行时的语义上有意义的变异。基于这一观察,我们认为,有可能用(一)美元来用高一代质量的预先训练的基因化模型来缓解交易。 美元(二),侧重于发现曲性方向作为分解的代谢学习的因素。为了实现这一点,我们建议通过Contrast(Dico)进行分解,作为根据目标分解的表达方式来模拟变异变的框架,并将变异以共同发现分解的方向和学习不相交错的代号。Disco-destrictal-degrational-degrational-degrational-degrational-degrational-degrational-degrational-degrational-degrational-destristraction-demodustrismismexmexmmal-demodustrismismal