Noting the importance of factorizing or disentangling the latent space, we propose a novel framework for autoencoders based on the principles of symmetry transformations in group-theory, which is a non-probabilistic disentangling autoencoder model. To the best of our knowledge, this is the first model that is aiming to achieve disentanglement based on autoencoders without regularizers. The proposed model is compared to seven state-of-the-art generative models based on autoencoders and evaluated based on reconstruction loss and five metrics quantifying disentanglement losses. The experiment results show that the proposed model can have better disentanglement when variances of each features are different. We believe that this model leads a new field for disentanglement learning based on autoencoders without regularizers.

本文介绍了一种使用对称变换原则的新型非概率解缠框架，用于对自动编码器中的潜在空间进行因式分解（或解缠），旨在实现不使用正则化器基于自动编码器的解缠，该模型与7种最先进的基于自动编码器的生成模型进行了比较，并根据5个监督解缠度量进行了评估，实验结果表明，所提出的模型在每个特征的差异方差比较大时可以获得更好的解缠效果。我们认为，这种模型开创了一个不使用正则化器来进行自动编码器的解缠学习的新领域。

解缠自编码器 (DAE)