VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties. VAE based on KL divergence has been considered as an effective technique for data augmentation. In this paper, we propose the use of Wasserstein distance as a measure of distributional similarity for the latent attributes, and show its superior theoretical lower bound (ELBO) compared with that of KL divergence under mild conditions. Using multiple experiments, we demonstrate that the new loss function exhibits better convergence property and generates artificial images that could better aid the image classification tasks.

翻译：VAE或变式自动编码器将数据压缩成潜在属性,并生成不同品种的新数据。基于 KL 差异的 VAE 被认为是增强数据的有效技术。 在本文中,我们提议使用瓦瑟斯坦距离作为潜在属性分布相似性的一种衡量尺度,并显示其优劣的理论约束(ELBO)比轻度条件下的KL差值(ELBO)低。我们通过多次实验,证明新的损失函数显示出更好的趋同属性,并生成能够更好地帮助图像分类任务的人工图像。