Research map / Learning theory and algorithms / Clustering
Uncover Underlying Correspondence for Robust Multi-view Clustering
Haochen Zhou, Guofeng Ding, Mouxing Yang, Peng Hu, Yijie Lin, Xi Peng
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 generative EM objective instead of vanilla InfoNCE (ablation) | CorreGen · Scene15 (MR 0.0, CR 0.0) | ACC: 47.83 -> 50.25 | Improved |
| add generative EM objective instead of vanilla InfoNCE (ablation) | CorreGen · UMPC-Food101 (MR 0.0, CR 0.0) | ACC: 48.47 -> 49.77 | Improved |
| add generative EM objective instead of vanilla InfoNCE (ablation) | CorreGen · Scene15 (MR 0.2, CR 0.2) | ACC: 38.36 -> 41.78 | Improved |
| add virtual sample module (ablation) | CorreGen · Scene15 (MR 0.0, CR 0.0) | ACC: 49.44 -> 50.25 | Improved |
| add virtual sample module (ablation) | CorreGen · UMPC-Food101 (MR 0.2, CR 0.2) | ACC: 44.01 -> 45.97 | Improved |
| add virtual sample module (ablation) | CorreGen · UMPC-Food101 (MR 0.0, CR 0.0) | NMI: 59.22 -> 58.36 | Hurt |
| add GMM-guided marginal estimation (ablation) | CorreGen · Scene15 (MR 0.0, CR 0.0) | ACC: 49.06 -> 50.25 | Improved |
| add GMM-guided marginal estimation (ablation) | CorreGen · UMPC-Food101 (MR 0.2, CR 0.2) | ACC: 44.59 -> 45.97 | Improved |
| add both virtual samples and GMM guide (ablation) | CorreGen · Scene15 (MR 0.2, CR 0.2) | ACC: 40.52 -> 41.78 | Improved |
| use CorreGen instead of DIVIDE base model (ablation) | CorreGen on DIVIDE · UMPC-Food101 (mismatch ratio 20%) | ACC: 31.41 -> 46.76 | Improved |
| use CorreGen instead of DIVIDE base model (ablation) | CorreGen on DIVIDE · Scene15 (MR 0.5, CR 0.5) | ACC: 30.27 -> 36.19 | Improved |
| use CorreGen instead of DIVIDE base model (ablation) | CorreGen on DIVIDE · Scene15 (mismatch ratio 0%) | ACC: 44.57 -> 50.25 | Improved |
Closest papers by meaning
- Robust Multi-view Clustering against Imperfect Information (NeurIPS 2026 · similarity 0.92)
- Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence (NeurIPS 2024 · similarity 0.90)
- Semantic Invariant Multi-View Clustering With Fully Incomplete Information (TPAMI 2023 · similarity 0.90)
- Transport Barycenter-Guided Sample-to-Cluster Matching for Unaligned Multi-view Clustering (TPAMI 2026 · similarity 0.89)
- ROLL: Robust Noisy Pseudo-label Learning for Multi-View Clustering with Noisy Correspondence (CVPR 2025 · similarity 0.89)
- Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios (CVPR 2024 · 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.
