Research map / Label-efficient and robust learning / Recognition and long-tail
Trusted Multi-View Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Fuse view-specific evidence and uncertainty with Dempster-Shafer theory rather than use the best single view | TMC · PIE | ACC: 84.36±0.87 -> 91.99±1.01 | Helped |
| Fuse view-specific evidence and uncertainty with Dempster-Shafer theory rather than use the best single view | TMC · Scene15 | ACC: 52.96±1.17 -> 67.74±0.36 | Helped |
| Fuse view-specific evidence and uncertainty with Dempster-Shafer theory rather than use the best single view | TMC · CUB | AUROC: 99.29±0.03 -> 99.06±0.03 | Hurt |
| Fuse view-specific evidence and uncertainty with Dempster-Shafer theory rather than use the best single view | TMC · Caltech101 | AUROC: 99.94±0.01 -> 99.90±0.01 | Hurt |
| Add View 1 (ablation) | TMC · PIE | ACC: 87.06±0.36 -> 91.99±1.01 | Helped |
| Add View 2 (ablation) | TMC · PIE | ACC: 89.56±0.55 -> 91.99±1.01 | Helped |
| Add View 3 (ablation) | TMC · PIE | ACC: 84.12±0.36 -> 91.99±1.01 | Helped |
| Add View 1 (ablation) | TMC · Scene15 | ACC: 63.65±0.43 -> 67.74±0.36 | Helped |
| Add View 2 (ablation) | TMC · Scene15 | ACC: 55.66±0.55 -> 67.74±0.36 | Helped |
| Add View 3 (ablation) | TMC · Scene15 | ACC: 64.41±0.53 -> 67.74±0.36 | Helped |
| Use evidence-level, uncertainty-aware fusion across multiple views | TMC · Multi-view data with Gaussian noise | accuracy | Helped |
Closest papers by meaning
- Enhancing Testing-Time Robustness for Trusted Multi-View Classification in the Wild (CVPR 2025 · similarity 0.90)
- Trusted Multi-View Classification with Expert Knowledge Constraints (ICML 2025 · similarity 0.90)
- Enhancing Multi-View Classification Reliability with Adaptive Rejection (AAAI 2025 · similarity 0.90)
- Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification (AAAI 2025 · similarity 0.89)
- Navigating Conflicting Views: Harnessing Trust for Learning (ICML 2025 · similarity 0.88)
- Deep Fuzzy Multi-view Learning for Reliable Classification (ICML 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.