Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks. In this work, we present methods to train Invertible Neural Networks (INNs) as (variational) autoencoders which we call INN (variational) autoencoders. Our experiments on MNIST, CIFAR and CelebA show that for low bottleneck sizes our INN autoencoder achieves results similar to the classical autoencoder. However, for large bottleneck sizes our INN autoencoder outperforms its classical counterpart. Based on the empirical results, we hypothesize that INN autoencoders might not have any intrinsic information loss and thereby are not bounded to a maximal number of layers (depth) after which only suboptimal results can be achieved.

翻译：自编码器能够以无监督学习的方式获取有用的数据表示，并已广泛应用于各类机器学习和计算机视觉任务中。本研究提出将可逆神经网络（INN）训练为（变分）自编码器的方法，我们称之为INN（变分）自编码器。在MNIST、CIFAR和CelebA数据集上的实验表明：当瓶颈层尺寸较小时，我们的INN自编码器性能与经典自编码器接近；但在瓶颈层尺寸较大的情况下，INN自编码器则优于经典自编码器。基于这些实证结果，我们推测INN自编码器可能不存在内在信息损失，因此其性能不会受限于最大层数（深度）——即不会出现因层数增加而只能获得次优解的情况。