AET vs. AED：通过自动编码转换而不是数据的无监督表示学习
AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data
摘要：
深度神经网络的成功通常依赖于大量的标记示例，而这些示例在许多真实场景中可能很难获得。为了应对这一挑战，无监督方法在不使用任何标记数据的情况下训练神经网络是非常可取的。在本文中，我们提出了一种新的范式，无监督的表示学习的自动编码转换（AET）相比，传统的自动编码数据（AED）的方法。给定一个随机采样的变换，AET试图在输出端尽可能准确地仅从编码特征预测它。其思路如下：只要无监督特征成功地编码了关于原始图像和变换图像的视觉结构的基本信息，就可以很好地预测变换。我们将展示这种AET范式允许我们实例化各种各样的转换，从参数化到非参数化和GAN诱导的转换。我们的实验表明，AET大大改善了现有的无监督方法，在CIFAR-10，ImageNet和Places数据集上设置了新的最先进的性能，大大接近其完全监督的上限。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
