Research map / Learning theory and algorithms / Clustering
Balanced Multi-View Clustering
Zhenglai Li, Jun Wang, Chang Tang, Xinzhong Zhu, Wei Zhang, Xinwang Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add view-specific contrastive regularization to reconstruction loss (ablation) | BMvC · Youtube | ACC: 27.48 -> 47.67 | Improved |
| add view-specific contrastive regularization to reconstruction loss (ablation) | BMvC · CUB | ACC: 78.54 -> 86.67 | Improved |
| add view-specific contrastive regularization to reconstruction loss (ablation) | BMvC · HW | ACC: 90.77 -> 97.95 | Improved |
| add view-specific contrastive regularization to reconstruction loss (ablation) | BMvC · xmedia | ACC: 85.21 -> 90.43 | Improved |
| add reconstruction loss to VCR-only training (ablation) | BMvC · OutdoorScene | ACC: 73.49 -> 78.46 | Improved |
| add reconstruction loss to VCR-only training (ablation) | BMvC · nuswide | ACC: 68.06 -> 66.49 | Hurt |
| add reconstruction loss to VCR-only training (ablation) | BMvC · Youtube | ACC: 42.91 -> 47.67 | Improved |
| use concatenation instead of average addition for fusion (ablation) | BMvC · CUB | ACC: 89.30 -> 86.67 | Hurt |
| use concatenation instead of average addition for fusion (ablation) | BMvC · xmedia | ACC: 90.97 -> 90.43 | Hurt |
| use concatenation instead of weighted addition for fusion (ablation) | BMvC · xmedia | ACC: 87.15 -> 90.43 | Improved |
| vary fusion manner (average, weighted, concatenation) (ablation) | BMvC · eight datasets | ACC | No clear effect |
| vary lambda trade-off in 1 to 1000 (ablation) | BMvC · eight datasets | ACC | No clear effect |
Closest papers by meaning
- Two Decades of Multi-View Clustering: Taxonomy, Application, and Challenge (TPAMI 2025 · similarity 0.92)
- EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering (CVPR 2025 · similarity 0.90)
- Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios (CVPR 2024 · similarity 0.90)
- Mixture of Experts as Representation Learner for Deep Multi-View Clustering (AAAI 2025 · similarity 0.89)
- PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering (ICML 2025 · similarity 0.89)
- Enhanced then Progressive Fusion with View Graph for Multi-View Clustering (CVPR 2025 · similarity 0.88)
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.
