Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations

INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108(2019)

引用 19|浏览1502
暂无评分
摘要
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost function to achieve this goal. We first show that these modifications, e.g. beta-VAE, simplify the tendency of variational inference to underfit causing pathological over-pruning and over-orthogonalization of learned components. Second we propose a complementary approach: to modify the probabilistic model with a structured latent prior. This prior allows to discover latent variable representations that are structured into a hierarchy of independent vector spaces. The proposed prior has three major advantages: First, in contrast to the standard VAE normal prior the proposed prior is not rotationally invariant. This resolves the problem of unidentifiability of the standard VAE normal prior. Second, we demonstrate that the proposed prior encourages a disentangled latent representation which facilitates learning of disentangled representations. Third, extensive quantitative experiments demonstrate that the prior significantly mitigates the trade-off between reconstruction loss and disentanglement over the state of the art.
更多
查看译文
关键词
independent subspace analysis,unsupervised learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要