AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process

Yingjie Ge, Kun Zhou, Jieyu Zhao, Xulun Ye

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MC-H, an adaptive multi-granularity deep clustering framework in hyperspherical space that combines Dynamic Prototype-Center Assignment with a hyperspherical determinantal point process.

Problem

Deep clustering struggles when coarse-grained and fine-grained semantic categories coexist in one dataset, since a single unified partitioning either over-separates coarse categories or misses subtle fine-grained differences.

Approach

Adapts clustering granularity by combining Dynamic Prototype-Center Assignment (DPCA) with a hyperspherical determinantal point process (DPP) so that prototypes/clusters are modeled at multiple granularities in a hyperspherical embedding space.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy