AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Reliable Clustering Number Estimation for Contrastive Multi-View Clustering

Zhengzhong Zhu, Pei Zhou, Lanxi Bai, Li Cheng, Jia Nie, Shiquan Min, Jiangping Zhu

CVPR 2026 · Learning theory and algorithms › Clustering · approach: Incomplete multi-view clustering

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add clustering guidance loss L_clu on top of L_rec + L_sacl (ablation)RCNMC · MNIST-USPSNMI: 0.914 -> 0.955Improved
add semantics-aware contrastive loss L_sacl on top of L_rec + L_clu (ablation)RCNMC · MNIST-USPSNMI: 0.875 -> 0.955Improved
add L_sacl to L_rec only (ablation)RCNMC · MNIST-USPSNMI: 0.498 -> 0.914Improved
add L_sacl on top of L_rec + L_clu (ablation)RCNMC · ProkaryoticACC: 0.625 -> 0.706Improved
add L_clu on top of L_rec + L_sacl (ablation)RCNMC · Synthetic3dACC: 0.965 -> 0.976Improved
learn K with RL instead of fixing a wrong K=2 (ablation)RCNMC · BDGPACC: 39.91 -> 99.2Improved
use RL cluster number learning instead of retraining for each K with the Elbow methodRCNMC · BDGP, Synthetic3dtraining timeImproved
Elbow method (WSS) for choosing Kbaseline RCNMC · Synthetic3dK selection clarityHurt
use RCNMC with estimated K versus baselines given ground-truth Kcontrastive MVC · MNIST-USPSACC: 0.972 -> 0.981Mixed
adaptive JSD-based view weighting (ablation)RCNMC · Synthetic3dview weightsImproved

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