In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural
networks which learn a low dimensional representation of data which are
additionally enriched with a desired structure in this low dimensional space.
While traditional Autoencoders have proven to structure data naturally they
fail to discover semantic structure that is hard to recognize in the raw data.
The SAE solves the problem by enhancing a traditional Autoencoder using weak
supervision to form a structured latent space. In the experiments we
demonstrate, that the structured latent space allows for a much more efficient
data representation for further tasks such as classification for sparsely
labeled data, an efficient choice of data to label, and morphing between
classes. To demonstrate the general applicability of our method, we show
experiments on the benchmark image datasets MNIST, Fashion-MNIST, DeepFashion2
and on a dataset of 3D human shapes.

本文提出了一种称为 Structuring AutoEncoders 的神经网络，其可以使用弱监督形成结构化的低维空间，从而更有效地表示并分类数据。在基准图像数据集 MNIST、Fashion-MNIST、DeepFashion2 以及 3D 人体形状数据集上进行的实验表明，结构潜空间可以为进一步的分类任务和分类数据的有效选择的操作提供更高效的表征。