Research map / Learning theory and algorithms / Clustering
Deep Online Probability Aggregation Clustering
Yuxuan Yan, Na Lu, Ruofan Yan
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 |
|---|---|---|---|
| use OPA self-labeling loss instead of directly minimizing J_pac (ablation) | DPAC · CIFAR-100 | ACC (%): 50.2 -> 51.6 | Improved |
| use OPA instead of J_pac on ImageNet-Dogs (ablation) | DPAC · ImageNet-Dogs | ACC (%): 53.9 -> 65.5 | Improved |
| use weighted contrastive loss instead of standard contrastive loss (ablation) | DPAC opa · CIFAR-10 | ACC (%): 89.7 -> 90.8 | Improved |
| use SimCLR-style framework instead of MoCo with OPA (ablation) | OPA · CIFAR-10 | ACC (%): 86.5 -> 89.7 | Improved |
| add cluster-size regularization term to OPA (ablation) | DPAC opa · CIFAR-10 | ACC (%): 90.7 -> 0.1 | Hurt |
| remove clustering regularization from SCAN (ablation) | SCAN · CIFAR-10 | ACC (%): 85.7 -> 0.1 | Hurt |
| remove clustering regularization from CC (ablation) | CC · CIFAR-10 | ACC (%): 79.2 -> 68.7 | Hurt |
| add self-labeling fine-tuning (ablation) | DPAC opa · ImageNet-Dogs | ACC (%): 65.5 -> 72.6 | Improved |
| use PAC centerless clustering vs RCC on entangled data | PAC · MNIST | ACC (%): 65.7 -> 59.7 | Hurt |
| use PAC instead of other clustering on pretrained deep features of subtle-class datasets | PAC · ImageNet-Dogs (deep features) | ACC (%): 52.6 -> 47.3 | No clear effect |
Closest papers by meaning
- DeepDPM: Deep Clustering With an Unknown Number of Clusters (CVPR 2022 · similarity 0.88)
- Deep Semantic Clustering by Partition Confidence Maximisation (CVPR 2020 · similarity 0.86)
- Samples Are Not Equal: A Sample Selection Approach for Deep Clustering (ICLR 2026 · similarity 0.86)
- Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation (AAAI 2024 · similarity 0.85)
- You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering (NeurIPS 2025 · 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.
