Research map / Label-efficient and robust learning / Recognition and long-tail
Uncertainty-Guided View-Strength-Aware Feature Utilization for Multi-View Classification
Li Lv, Qian Guo, Li Zhang, Liang Du, Bingbing Jiang, Lu Chen, Xinyan Liang
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 Differentiated Feature Selector (DFS) (ablation) | UVF · AWA | accuracy (%): 82.27 -> 89.69 | Improved |
| add DFS (ablation) | UVF · Reuters5 | accuracy (%): 77.48 -> 80.59 | Improved |
| add strength-guided gating (SG) on top of DFS (ablation) | UVF · VoxCeleb | accuracy (%): 91.17 -> 93.24 | Improved |
| add SG on top of DFS (ablation) | UVF · AWA | accuracy (%): 89.69 -> 89.69 | No clear effect |
| add SG on top of DFS (ablation) | UVF · YoutubeFace | accuracy (%): 85.59 -> 85.59 | No clear effect |
| add uncertainty-guided fusion (UG) on top of DFS (ablation) | UVF · AWA | accuracy (%): 89.69 -> 90.98 | Improved |
| add UG on top of DFS (ablation) | UVF · YoutubeFace | accuracy (%): 85.59 -> 85.32 | Hurt |
| add UG alone without DFS (ablation) | UVF · AWA | accuracy (%): 82.27 -> 82.46 | No clear effect |
| add all three modules (DFS, SG, UG) over the plain baseline (ablation) | UVF · VoxCeleb | accuracy (%): 90.06 -> 94.18 | Improved |
| add prediction uncertainty weighting (PU) (ablation) | UVF · Reuters5 | accuracy (%): 81.07 -> 81.88 | Improved |
| add cognitive uncertainty weighting (CU) (ablation) | UVF · Reuters5 | accuracy (%): 81.07 -> 81.30 | Improved |
| add CU on top of PU (ablation) | UVF · Reuters3 | accuracy (%): 85.68 -> 86.09 | Improved |
Closest papers by meaning
- Trusted Multi-View Classification (ICLR 2021 · similarity 0.88)
- Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification (AAAI 2025 · similarity 0.88)
- Enhancing Multi-View Classification Reliability with Adaptive Rejection (AAAI 2025 · similarity 0.87)
- Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection (AAAI 2025 · similarity 0.86)
- Deep Fuzzy Multi-view Learning for Reliable Classification (ICML 2025 · similarity 0.84)
- Enhancing Testing-Time Robustness for Trusted Multi-View Classification in the Wild (CVPR 2025 · 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.
