GAN-EM: GAN based EM learning framework
GAN-EM: GAN based EM learning framework
复制标题
DOI：
10.24963/ijcai.2019/612
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Wentian Zhao;Shaojie Wang;Zhihuai Xie;Jing Shi;Chenliang Xu
中科院分区：
文献类型：
--
作者：
Wentian Zhao;Shaojie Wang;Zhihuai Xie;Jing Shi;Chenliang Xu
期望最大化（EM）算法是求具有潜在变量的模型的最大似然解.一个典型的例子是高斯混合模型（GMM），它需要高斯假设，然而，自然图像是高度非高斯的，使得GMM不能应用于执行像素空间上的图像聚类任务。为了克服这种限制，我们提出了一个基于GAN的EM学习框架，可以最大限度地提高图像的可能性并估计潜在变量。我们将此模型称为GAN-EM，它是图像聚类、半监督分类和降维的框架。在M步中，我们设计了一个新的损失函数，用于GAN的最大似然估计（MLE）的数据与软类标签分配。具体地说，条件生成器捕获K个类的数据分布，而样本生成器告诉每个类的样本是真实的还是假的。由于该模型是无监督的，因此将真实的数据的类别标签作为潜在变量，在E步中通过一个附加网络（E-net）进行估计。所提出的GAN-EM在MNIST、SVHN和CelebA上实现了最先进的聚类和半监督分类结果，并且生成的图像质量与其他最近开发的生成模型相当。
Expectation maximization (EM) algorithm is to find maximum likelihood solution for models having latent variables. A typical example is Gaussian Mixture Model (GMM) which requires Gaussian assumption, however, natural images are highly non-Gaussian so that GMM cannot be applied to perform image clustering task on pixel space. To overcome such limitation, we propose a GAN based EM learning framework that can maximize the likelihood of images and estimate the latent variables. We call this model GAN-EM, which is a framework for image clustering, semi-supervised classification and dimensionality reduction. In M-step, we design a novel loss function for discriminator of GAN to perform maximum likelihood estimation (MLE) on data with soft class label assignments. Specifically, a conditional generator captures data distribution for K classes, and a discriminator tells whether a sample is real or fake for each class. Since our model is unsupervised, the class label of real data is regarded as latent variable, which is estimated by an additional network (E-net) in E-step. The proposed GAN-EM achieves state-of-the-art clustering and semi-supervised classification results on MNIST, SVHN and CelebA, as well as comparable quality of generated images to other recently developed generative models.