The success of deep neural networks often relies on a large amount of labeled examples, which can be difficult to obtain in many real scenarios. To address this challenge, unsupervised methods are strongly preferred for training neural networks without using any labeled data. In this paper, we present a novel paradigm of unsupervised representation learning by Auto-Encoding Transformation (AET) in contrast to the conventional Auto-Encoding Data (AED) approach. Given a randomly sampled transformation, AET seeks to predict it merely from the encoded features as accurately as possible at the output end. The idea is the following: as long as the unsupervised features successfully encode the essential information about the visual structures of original and transformed images, the transformation can be well predicted. We will show that this AET paradigm allows us to instantiate a large variety of transformations, from parameterized, to non-parameterized and GAN-induced ones. Our experiments show that AET greatly improves over existing unsupervised approaches, setting new state-of-the-art performances being greatly closer to the upper bounds by their fully supervised counterparts on CIFAR-10, ImageNet and Places datasets.

本文提出了一种新的无监督表示学习范式，通过自编码变换（AET）而非传统的自编码数据（AED）方法进行训练，使得神经网络可以在没有标注数据的情况下学习。实验结果表明，AET范式可以实例化一大类变换，具有比现有的无监督方法更好的性能，特别是在CIFAR-10、ImageNet和Places数据集上表现更接近完全监督对照组的上限。

AET vs. AED: 通过自编码变换而非数据进行无监督表示学习