Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Comprehensive Correlation Mining for Image Clustering
Jianlong Wu, Keyu Long, Fei Wang, Chen Qian, Cheng Li, Zhouchen Lin, Hongbin Zha
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 local robustness (transformed-sample pseudo-graph and loss) (ablation) | DCCM · CIFAR-10 | ACC: 0.405 -> 0.512 | Improved |
| add local robustness (ablation) | DCCM · CIFAR-10 | NMI: 0.304 -> 0.412 | Improved |
| add pseudo-label loss (ablation) | DCCM · CIFAR-10 | ACC: 0.512 -> 0.583 | Improved |
| add pseudo-label loss (ablation) | DCCM · CIFAR-10 | NMI: 0.412 -> 0.448 | Improved |
| add triplet mutual information loss (ablation) | DCCM · CIFAR-10 | ACC: 0.583 -> 0.623 | Improved |
| add triplet mutual information loss (ablation) | DCCM · CIFAR-10 | ARI: 0.358 -> 0.408 | Improved |
| raise pseudo-label confidence threshold (ablation) | DCCM · CIFAR-10 | clustering performance | Improved |
| sample negatives randomly instead of farthest negatives for MI pairs (ablation) | DCCM · CIFAR-10 | classification ACC (Y64): 0.713 -> 0.744 | Improved |
| sample positives nearest instead of random for MI pairs (ablation) | DCCM · CIFAR-10 | classification ACC (Y64): 0.731 -> 0.744 | Improved |
| sample uniformly in the minibatch instead of top-n confident positives (ablation) | DCCM · CIFAR-10 | classification ACC (Y64): 0.698 -> 0.744 | Improved |
| replace DAC with DCCM under same architecture | DCCM · CIFAR-10 | clustering ACC: 0.514 -> 0.623 | Improved |
| replace DAC with DCCM | DCCM · CIFAR-100 (20 superclasses) | ACC: 0.238 -> 0.327 | Improved |
Closest papers by meaning
- Invariant Information Clustering for Unsupervised Image Classification and Segmentation (ICCV 2019 · similarity 0.88)
- Deep Adaptive Image Clustering (ICCV 2017 · similarity 0.88)
- Improved Approximation Algorithms for Chromatic and Pseudometric-Weighted Correlation Clustering (NeurIPS 2025 · similarity 0.87)
- Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models (ICLR 2024 · similarity 0.86)
- Hierarchical Correlation Clustering and Tree Preserving Embedding (CVPR 2024 · similarity 0.86)
- Interactive Deep Clustering via Value Mining (NeurIPS 2024 · similarity 0.85)
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.
