使用增强生成对抗网络与信息最大化的图像聚类
Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
AI总结：
本文提出一种结合改进GAN与辅助分类器的深度聚类框架，通过Sobel操作增强特征可分离性并利用多聚类头处理不平衡数据，在CIFAR-10/100等数据集上取得优于现有方法的聚类性能。
摘要：
由于未标注数据集的可获得性不断提高，图像聚类近年来引起了广泛关注。传统聚类算法的效率在很大程度上依赖于所使用的距离函数和特征的维度。因此，在处理未经处理的图像或从已处理图像中提取的高维特征时，常常会出现性能下降。为了应对这些挑战，我们提出了一种深度聚类框架，该框架由一个改进的生成对抗网络（GAN）和一个辅助分类器组成。该改进在GAN的判别器之前采用Sobel操作，以增强所学特征的可分离性。然后利用判别器生成表示，作为辅助分类器的输入。采用自适应目标函数训练辅助分类器以对表示进行聚类，旨在通过最小化判别器生成的多个表示之间的散度来提高鲁棒性。辅助分类器由一组多个聚类头实现，其中使用一个容忍超参数来处理不平衡数据。我们的结果表明，所提出的方法在CIFAR-10和CIFAR-100上显著优于最先进的聚类方法，并且在STL10和MNIST数据集上具有竞争力。
英文摘要：
Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets. The efficiency of traditional clustering algorithms heavily depends on the distance functions used and the dimensionality of the features. Therefore, performance degradation is often observed when tackling either unprocessed images or high-dimensional features extracted from processed images. To deal with these challenges, we propose a deep clustering framework consisting of a modified generative adversarial network (GAN) and an auxiliary classifier. The modification employs Sobel operations prior to the discriminator of the GAN to enhance the separability of the learned features. The discriminator is then leveraged to generate representations as the input to an auxiliary classifier. An adaptive objective function is utilised to train the auxiliary classifier for clustering the representations, aiming to increase the robustness by minimizing the divergence of multiple representations generated by the discriminator. The auxiliary classifier is implemented with a group of multiple cluster-heads, where a tolerance hyper-parameter is used to tackle imbalanced data. Our results indicate that the proposed method significantly outperforms state-of-the-art clustering methods on CIFAR-10 and CIFAR-100, and is competitive on the STL10 and MNIST datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
