A self-supervised learning of semantic feature consistency for image clustering

Article type: Research Article

Authors: Chen, Junfen | Han, Jie | Xie, Bojun^{; *} | Li, Nana

Affiliations: Key Laboratory of Machine Learning and Computational Intelligence of Hebei Province, College of Mathematics and Information Science, Hebei University, Baoding, China

Correspondence: [*] Corresponding author. Bojun Xie. E-mail: xiebojun@126.com.

Abstract: Contrastive learning is a powerful technique for learning feature representations without manual annotation. The K-nearest neighbor (KNN) method is commonly used to construct positive sample pairs to calculate the contrastive loss. However, it is challenging to distinguish positive sample pairs, reducing clustering performance. We propose a novel Deep Contrastive Clustering method based on a GrapH convolutional network called GHDCC. It uses an instance-level contrastive loss with mean square error (MSE) regularization and a cluster-level contrastive loss to incorporate semantic features and perform cluster assignments. The method utilizes a graph convolutional network (GCN) to improve the semantic consistency of features and linear interpolation data augmentation to improve the representation ability of the model. To minimize the occurrence of false positive sample pairs, we select only samples whose similarity exceeds a predefined threshold to construct the adjacency matrix. The experimental results on six public datasets demonstrate that the GHDCC significantly outperforms contrastive clustering (CC, 500) by a large margin except on CIFAR-10. The GHDCC performs well compared to other deep contrastive clustering methods and achieves the highest clustering accuracy of 0.913 on ImageNet-10.

Keywords: Self-supervised clustering, graph convolutional network, linear interpolation data augmentation, contrastive learning

DOI: 10.3233/JIFS-230208

Journal: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 8651-8661, 2023