DNB: A Joint Learning Framework for Deep Bayesian Nonparametric Clustering
DNB: A Joint Learning Framework for Deep Bayesian Nonparametric Clustering
复制标题
DOI：
10.1109/tnnls.2021.3085891
复制
发表时间：
2021-06
影响因子：
10.4
通讯作者：
Zeya Wang;Yang Ni;Baoyu Jing;Deqing Wang;Hao Zhang;E. Xing
中科院分区：
文献类型：
--
作者：
Zeya Wang;Yang Ni;Baoyu Jing;Deqing Wang;Hao Zhang;E. Xing
基于深度神经网络的聚类算法在图像分析中得到了广泛的研究。大多数现有的方法需要对真标签的部分知识，即聚类的数量，这在实践中通常是不可用的。在本文中，我们提出了一个贝叶斯非参数框架，深度非参数贝叶斯（DNB），用于以双重无监督的方式联合学习图像聚类和深度表示。在双重无监督学习中，我们处理的是“未知的未知数”问题，我们不仅要估计未知的图像标签，还要估计未知的标签数量。该算法在向前传递过程中生成无限数量的聚类，在向后传递过程中学习深度网络。利用Dirichlet过程混合，该方法能够在不指定先验簇数的情况下对潜在表示空间进行划分。这项工作的一个重要特点是，所有的估计都是通过端到端解决方案实现的，这与依赖于事后分析来选择集群数量的方法有很大的不同。本文的另一个关键思想是为深度聚类的“平凡解”问题提供一个原则性的解决方案，这在目前的文献中还没有太多的研究。通过对基准数据集的大量实验，我们证明了我们的双无监督方法取得了良好的聚类性能，并且优于许多其他的无监督图像聚类方法。
Clustering algorithms based on deep neural networks have been widely studied for image analysis. Most existing methods require partial knowledge of the true labels, namely, the number of clusters, which is usually not available in practice. In this article, we propose a Bayesian nonparametric framework, deep nonparametric Bayes (DNB), for jointly learning image clusters and deep representations in a doubly unsupervised manner. In doubly unsupervised learning, we are dealing with the problem of “unknown unknowns,” where we estimate not only the unknown image labels but also the unknown number of labels as well. The proposed algorithm alternates between generating a potentially unbounded number of clusters in the forward pass and learning the deep networks in the backward pass. With the help of the Dirichlet process mixtures, the proposed method is able to partition the latent representations space without specifying the number of clusters a priori. An important feature of this work is that all the estimation is realized with an end-to-end solution, which is very different from the methods that rely on post hoc analysis to select the number of clusters. Another key idea in this article is to provide a principled solution to the problem of “trivial solution” for deep clustering, which has not been much studied in the current literature. With extensive experiments on benchmark datasets, we show that our doubly unsupervised method achieves good clustering performance and outperforms many other unsupervised image clustering methods.