4 papers
Dual-Level Cross-Modal Contrastive Clustering
Haixin Zhang, Yongjun Li, Dong Huang
Image clustering, which involves grouping images into different clusters without labels, is a key task in unsupervised learning. Although previous deep clustering methods have achi…
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction
Hai-Xin Zhang, Dong Huang, Hua-Bao Ling +3
In this paper, we present a novel deep image clustering approach termed PICI, which enforces the partial information discrimination and the cross-level interaction in a joint learn…
Deep Clustering with Diffused Sampling and Hardness-aware Self-distillation
Hai-Xin Zhang, Dong Huang
Deep clustering has gained significant attention due to its capability in learning clustering-friendly representations without labeled data. However, previous deep clustering metho…
Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype Aggregation
Haixin Zhang, Dong Huang
Previous contrastive deep clustering methods mostly focus on instance-level information while overlooking the member relationship within groups/clusters, which may significantly un…