Ding Shifei, Hou Haiwei, Xu Xiao, Zhang Jian, Guo Lili, Ding Ling
IEEE Trans Neural Netw Learn Syst. 2024 Dec;35(12):18828-18837. doi: 10.1109/TNNLS.2024.3367322. Epub 2024 Dec 2.
Image clustering is a research hotspot in machine learning and computer vision. Existing graph-based semi-supervised deep clustering methods suffer from three problems: 1) because clustering uses only high-level features, the detailed information contained in shallow-level features is ignored; 2) most feature extraction networks employ the step odd convolutional kernel, which results in an uneven distribution of receptive field intensity; and 3) because the adjacency matrix is precomputed and fixed, it cannot adapt to changes in the relationship between samples. To solve the above problems, we propose a novel graph-based semi-supervised deep clustering method for image clustering. First, the parity cross-convolutional feature extraction and fusion module is used to extract high-quality image features. Then, the clustering constraint layer is designed to improve the clustering efficiency. And, the output layer is customized to achieve unsupervised regularization training. Finally, the adjacency matrix is inferred by actual network prediction. A graph-based regularization method is adopted for unsupervised training networks. Experimental results show that our method significantly outperforms state-of-the-art methods on USPS, MNIST, street view house numbers (SVHN), and fashion MNIST (FMNIST) datasets in terms of ACC, normalized mutual information (NMI), and ARI.
图像聚类是机器学习和计算机视觉领域的一个研究热点。现有的基于图的半监督深度聚类方法存在三个问题：1）由于聚类仅使用高级特征，浅层特征中包含的详细信息被忽略；2）大多数特征提取网络采用步长为奇数的卷积核，这导致感受野强度分布不均匀；3）由于邻接矩阵是预先计算并固定的，它无法适应样本之间关系的变化。为了解决上述问题，我们提出了一种用于图像聚类的基于图的新型半监督深度聚类方法。首先，使用奇偶交叉卷积特征提取和融合模块来提取高质量的图像特征。然后，设计聚类约束层以提高聚类效率。并且，定制输出层以实现无监督正则化训练。最后，通过实际网络预测来推断邻接矩阵。采用基于图的正则化方法对无监督训练网络进行训练。实验结果表明，在USPS、MNIST、街景门牌号（SVHN）和时尚MNIST（FMNIST）数据集上，我们的方法在ACC、归一化互信息（NMI）和ARI方面显著优于现有方法。
