An autoencoder that learns a latent space in an unsupervised manner has many applications in signal processing. However, the latent space of an autoencoder does not pursue the same clustering goal as Kmeans or GMM. A recent work proposes to artificially re-align each point in the latent space of an autoencoder to its nearest class neighbors during training (Song et al. 2013). The resulting new latent space is found to be much more suitable for clustering, since clustering information is used. Inspired by previous works (Song et al. 2013), in this letter we propose several extensions to this technique. First, we propose a probabilistic approach to generalize Song's approach, such that Euclidean distance in the latent space is now represented by KL divergence. Second, as a consequence of this generalization we can now use probability distributions as inputs rather than points in the latent space. Third, we propose using Bayesian Gaussian mixture model for clustering in the latent space. We demonstrated our proposed method on digit recognition datasets, MNIST, USPS and SHVN as well as scene datasets, Scene15 and MIT67 with interesting findings.

中文翻译：

---

使用变分自编码器进行深度聚类

以无监督方式学习潜在空间的自编码器在信号处理中有许多应用。然而，自动编码器的潜在空间并不追求与 Kmeans 或 GMM 相同的聚类目标。最近的一项工作建议在训练期间人为地将自动编码器的潜在空间中的每个点重新对齐到其最近的类邻居（Song 等人，2013 年）。结果发现新的潜在空间更适合聚类，因为使用了聚类信息。受先前工作（Song 等人，2013 年）的启发，在这封信中，我们提出了对该技术的几种扩展。首先，我们提出了一种概率方法来概括宋的方法，使得潜在空间中的欧几里德距离现在由 KL 散度表示。第二，作为这种概括的结果，我们现在可以使用概率分布作为输入，而不是潜在空间中的点。第三，我们建议使用贝叶斯高斯混合模型在潜在空间中进行聚类。我们在数字识别数据集 MNIST、USPS 和 SHVN 以及场景数据集 Scene15 和 MIT67 上展示了我们提出的方法，并获得了有趣的发现。