Research map / Learning theory and algorithms / Clustering
DivClust: Controlling Diversity in Deep Clustering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DivClust diversity control (D^T=0.8) and consensus aggregation to CC | CC · CIFAR10 | ACC: 0.790 -> 0.819 | Helped |
| Add DivClust diversity control (D^T=0.7) and consensus aggregation to CC | CC · CIFAR100 | ACC: 0.429 -> 0.437 | Helped |
| Add DivClust diversity control (D^T=0.95) and consensus aggregation to CC | CC · ImageNet-10 | ACC: 0.893 -> 0.936 | Helped |
| Add DivClust diversity control (D^T=0.7) and consensus aggregation to CC | CC · ImageNet-Dogs | ACC: 0.429 -> 0.529 | Helped |
| Add DivClust diversity control and consensus aggregation | IIC · CIFAR10 | ACC: 0.442 -> 0.685 | Helped |
| Add DivClust diversity control and consensus aggregation | PICA · CIFAR10 | ACC: 0.533 -> 0.671 | Helped |
| Set the diversity target to D^T=1., disabling effective diversity control (ablation) | CC + DivClust consensus clustering · CIFAR10 | ACC: 0.790 -> 0.763 | No clear effect |
| Set the diversity target to D^T=0.9 (ablation) | CC + DivClust consensus clustering · CIFAR10 | ACC: 0.790 -> 0.789 | No clear effect |
| Set the diversity target to D^T=0.7 (ablation) | CC + DivClust consensus clustering · CIFAR10 | ACC: 0.790 -> 0.815 | Helped |
| Set the diversity target to D^T=0.7 (ablation) | CC + DivClust consensus clustering · ImageNet-10 | ACC: 0.893 -> 0.90 | Helped |
Closest papers by meaning
- Breaking the Reclustering Barrier in Centroid-based Deep Clustering (ICLR 2025 · similarity 0.86)
- You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering (NeurIPS 2025 · similarity 0.85)
- From Logits to Hierarchies: Hierarchical Clustering made Simple (ICML 2025 · similarity 0.85)
- Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation (AAAI 2024 · similarity 0.85)
- Deep Variational Incomplete Multi-View Clustering: Exploring Shared Clustering Structures (AAAI 2024 · similarity 0.84)
- Interactive Deep Clustering via Value Mining (NeurIPS 2024 · similarity 0.84)
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.