Research map / Learning theory and algorithms / Clustering
Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery
Xinhang Wan, Jiyuan Liu, Qian Qu, Suyuan Liu, Chuyu Zhang, Fangdi Wang, Xinwang Liu, En Zhu, Kunlun He
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 known-class view-weight guidance (alpha) (ablation) | IICMVNCD · BRCA | ACC: 58.79 -> 98.79 | Improved |
| add known-class data (D_l) in matrix factorization (ablation) | IICMVNCD · BRCA | ACC: 58.79 -> 98.79 | Improved |
| add both view-weight guidance and known-class factorization (ablation) | IICMVNCD · BRCA | ACC: 52.73 -> 98.79 | Improved |
| add known-class view-weight guidance (alpha) (ablation) | IICMVNCD · Cora | ACC: 56.66 -> 76.36 | Improved |
| add known-class data (D_l) in matrix factorization (ablation) | IICMVNCD · Cora | ACC: 42.20 -> 76.36 | Improved |
| add known-class view-weight guidance (alpha) (ablation) | IICMVNCD · Wiki | ACC: 35.44 -> 65.42 | Improved |
| add known-class data (D_l) in matrix factorization (ablation) | IICMVNCD · Wiki | ACC: 64.35 -> 65.42 | Improved |
| add known-class data (D_l) in matrix factorization (ablation) | IICMVNCD · YTB10 | ACC: 79.08 -> 94.55 | Improved |
| add known-class view-weight guidance (alpha) (ablation) | IICMVNCD · YTB10 | ACC: 94.32 -> 94.55 | Improved |
| add known-class view-weight guidance (alpha) (ablation) | IICMVNCD · STL10 | ACC: 98.95 -> 99.02 | No clear effect |
| add known-class data (D_l) in matrix factorization (ablation) | IICMVNCD · uci-digit | ACC: 93.80 -> 95.30 | Improved |
| use multi-view NCD instead of single-view NCD baselines (IIC) on Cora | IICMVNCD · Cora | ACC: 48.56 -> 76.36 | Improved |
Closest papers by meaning
- Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery (CVPR 2023 · similarity 0.89)
- A Unified Objective for Novel Class Discovery (ICCV 2021 · similarity 0.88)
- Joint Class-level and Instance-level Relationship Modeling for Novel Class Discovery (AAAI 2025 · similarity 0.87)
- Semantic-Guided Novel Category Discovery (AAAI 2024 · similarity 0.87)
- Novel Class Discovery in Chest X-rays via Paired Images and Text (AAAI 2024 · similarity 0.87)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · 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.
