Contrastive Hierarchical Clustering
This work addresses the problem of limited information in flat partitions for researchers and practitioners in deep clustering, offering a hierarchical approach that is incremental over existing methods.
The paper tackles the limitation of flat clustering models by introducing CoHiClust, a contrastive hierarchical clustering model for image data, which generates a binary tree structure without labeled data and achieves superior clustering accuracy on most image datasets compared to state-of-the-art flat models.
Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the ground truth on popular benchmarks, the information contained in the flat partition is limited. In this paper, we introduce CoHiClust, a Contrastive Hierarchical Clustering model based on deep neural networks, which can be applied to typical image data. By employing a self-supervised learning approach, CoHiClust distills the base network into a binary tree without access to any labeled data. The hierarchical clustering structure can be used to analyze the relationship between clusters, as well as to measure the similarity between data points. Experiments demonstrate that CoHiClust generates a reasonable structure of clusters, which is consistent with our intuition and image semantics. Moreover, it obtains superior clustering accuracy on most of the image datasets compared to the state-of-the-art flat clustering models.