2 code implementations • 16 Jun 2022 • Tong Wang, Guanyu Yang, Qijia He, Zhenquan Zhang, Junhua Wu
However, most existing methods 1) do not directly address the clustering task, since the representation learning and clustering process are separated; 2) depend too much on data augmentation, which greatly limits the capability of contrastive learning; 3) ignore the contrastive message for clustering tasks, which adversely degenerate the clustering results.