论文标题
学习分解的表示具有潜在差异可预测性的表示
Learning Disentangled Representations with Latent Variation Predictability
论文作者
论文摘要
潜在遍历是一种可视化分离的潜在表示的流行方法。考虑到潜在表示的单个单元中有一堆变化，可以预期，数据的单个变化因素会发生变化，而其他数据则是固定的。但是，这种令人印象深刻的实验观察很少在学习分解表示的目标函数中明确编码。本文定义了潜在分解表示的可预测性。给定的图像对由潜在代码在单个维度上变化而产生的图像对，如果表示表示良好，则可以与这些图像对密切相关。在对抗生成过程中，我们通过最大化潜在变化和相应图像对之间的相互信息来鼓励可预测性。我们进一步开发了一个评估指标，该指标不依赖于基础真相生成因素来衡量潜在表示的分离。所提出的变异可预测性是一种普遍的约束，适用于VAE和GAN框架，用于增强潜在表示的分离。实验表明，所提出的可预测性与现有的基地固定指标很好地相关，并且所提出的算法对于分解学习有效。
Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expected that there is a change in a single factor of variation of the data while others are fixed. However, this impressive experimental observation is rarely explicitly encoded in the objective function of learning disentangled representations. This paper defines the variation predictability of latent disentangled representations. Given image pairs generated by latent codes varying in a single dimension, this varied dimension could be closely correlated with these image pairs if the representation is well disentangled. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We further develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations. The proposed variation predictability is a general constraint that is applicable to the VAE and GAN frameworks for boosting disentanglement of latent representations. Experiments show that the proposed variation predictability correlates well with existing ground-truth-required metrics and the proposed algorithm is effective for disentanglement learning.
