Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Semantic Clustering by Partition Confidence Maximisation
Jiabo Huang, Shaogang Gong, Xiatian Zhu
Check 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 partition-confidence clustering instead of DCCM | PICA · CIFAR-10 | ACC: 0.623 -> 0.645 | Improved |
| use partition-confidence clustering instead of DCCM | PICA · CIFAR-100 | ACC: 0.327 -> 0.322 | No clear effect |
| use partition-confidence clustering instead of IIC | PICA · STL-10 | ACC: 0.610 -> 0.693 | Improved |
| use partition-confidence clustering instead of DCCM | PICA · ImageNet-10 | ACC: 0.710 -> 0.850 | Improved |
| use partition-confidence clustering instead of DCCM | PICA · ImageNet-Dogs | ACC: 0.383 -> 0.324 | Hurt |
| use partition-confidence clustering instead of DCCM | PICA · Tiny-ImageNet | ACC: 0.108 -> 0.094 | Hurt |
| reduce entropy regularisation weight from 7 to 3 (ablation) | PICA · CIFAR-10 | ACC: 0.246 -> 0.696 | Improved |
| reduce entropy regularisation weight from 7 to 3 (ablation) | PICA · CIFAR-100 | ACC: 0.168 -> 0.330 | Improved |
| reduce entropy regularisation weight from 7 to 3 (ablation) | PICA · ImageNet-10 | ACC: 0.650 -> 0.829 | Improved |
| add over-clustering head (ablation) | PICA · CIFAR-10 | ACC: 0.582 -> 0.696 | Improved |
| add over-clustering head (ablation) | PICA · STL-10 | ACC: 0.633 -> 0.687 | Improved |
| use the paper's standard perturbation setting rather than setting 7 (ablation) | PICA · CIFAR-10 | ACC: 0.310 -> 0.696 | Improved |
Closest papers by meaning
- DeepDPM: Deep Clustering With an Unknown Number of Clusters (CVPR 2022 · similarity 0.90)
- Samples Are Not Equal: A Sample Selection Approach for Deep Clustering (ICLR 2026 · similarity 0.89)
- Deep Clustering for Unsupervised Learning of Visual Features (ECCV 2018 · similarity 0.89)
- Objective-Based Hierarchical Clustering of Deep Embedding Vectors (AAAI 2021 · similarity 0.88)
- From Logits to Hierarchies: Hierarchical Clustering made Simple (ICML 2025 · similarity 0.87)
- Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering (CVPR 2025 · similarity 0.87)
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.
