Deep semi-supervised clustering based on pairwise constraints and sample similarity.

Semi-supervised clustering methods enhance the performance of completely unsupervised clustering tasks by incorporating pairwise relationship information from a subset of samples. However, previous methods based on pairwise constraints have struggled to effectively leverage available prior knowledge and fully exploit the similarity relationships between samples. To address these issues, this paper proposes an advanced approach called Deep Semi-Supervised Clustering based on Pairwise Constraints and Sample Similarity (DSCPS). Specifically, DSCPS consists of two training stages: the coarse clustering stage and the fine clustering stage. In the coarse clustering stage, DSCPS assigns probabilities to each sample indicating its belongingness to each cluster by computing the distance to the cluster centers. In the fine clustering stage, DSCPS introduces a predictor network in the clustering space to predict the class labels of each sample. Simultaneously, the thresholds for similarity and dissimilarity between samples are determined based on pairwise constraints. Finally, the encoder and prediction network are further optimized using sample similarity relationships and pairwise constraints as loss conditions, resulting in the final clustering results. Extensive experiments demonstrate that DSCPS outperforms state-of-the-art methods, achieving the highest performance. • Proposing a two-stage deep learning network for clustering with pairwise constraints. • Designing an iterative clustering training process with weighted assignments. • Larger weight losses are assigned to samples at the cluster boundaries. • Introducing a similarity loss to train the prediction network. [ABSTRACT FROM AUTHOR]