GCC: Generative Calibration Clustering

arXiv:2404.09115v1 Announce Type: new
Abstract: Deep clustering as an important branch of unsupervised representation learning focuses on embedding semantically similar samples into the identical feature space. This core demand inspires the exploration of contrastive learning and subspace clustering. However, these solutions always rely on the basic assumption that there are sufficient and category-balanced samples for generating valid high-level representation. This hypothesis actually is too strict to be satisfied for real-world applications. To overcome such a challenge, the natural strategy is …

abstract arxiv basic clustering core cs.cv demand embedding exploration feature gcc generative however representation representation learning samples solutions space type unsupervised