Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-View Information-Bottleneck Representation Learning
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 |
|---|---|---|---|
| combine shared and view-specific representations through the information bottleneck | CMIB-Nets · Handwritten | ACC: 85.62±1.82 -> 89.72±1.06 | Helped |
| combine shared and view-specific representations through the information bottleneck | CMIB-Nets · ORL | ACC: 68.85±2.11 -> 72.07±1.81 | Helped |
| combine shared and view-specific representations through the information bottleneck | CMIB-Nets · COIL20 | ACC: 74.25±2.56 -> 77.58±1.17 | Helped |
| combine shared and view-specific representations through the information bottleneck | CMIB-Nets · Caltech101 | ACC: 66.45±2.55 -> 71.02±0.98 | Helped |
| combine shared and view-specific representations through the information bottleneck | CMIB-Nets · BBCSport | ACC: 72.98±3.13 -> 77.13±1.63 | Helped |
| combine shared and view-specific representations through the information bottleneck | CMIB-Nets · CUB | ACC: 79.27±3.28 -> 80.37±2.06 | Helped |
| add the view-specific representation to the shared representation (ablation) | CMIB-Nets · Handwritten | ACC: 81.85±1.57 -> 89.72±1.06 | Helped |
| add the shared representation to the view-specific representation (ablation) | CMIB-Nets · Handwritten | ACC: 76.24±1.81 -> 89.72±1.06 | Helped |
| add the view-specific representation to the shared representation (ablation) | CMIB-Nets · BBCSport | ACC: 60.34±2.57 -> 77.13±1.63 | Helped |
| add the shared representation to the view-specific representation (ablation) | CMIB-Nets · BBCSport | ACC: 52.92±3.65 -> 77.13±1.63 | Helped |
| add the view-specific representation to the shared representation (ablation) | CMIB-Nets · CUB | ACC: 72.75±1.36 -> 80.37±2.06 | Helped |
| add the shared representation to the view-specific representation (ablation) | CMIB-Nets · CUB | ACC: 74.23±0.81 -> 80.37±2.06 | Helped |
Closest papers by meaning
- Differentiable Information Bottleneck for Deterministic Multi-view Clustering (CVPR 2024 · similarity 0.89)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.85)
- Structured IB: Improving Information Bottleneck with Structured Feature Learning (AAAI 2025 · similarity 0.85)
- Rethinking Multi-view Representation Learning via Distilled Disentangling (CVPR 2024 · similarity 0.85)
- Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view Clustering (AAAI 2025 · similarity 0.85)
- Mixture of Experts as Representation Learner for Deep Multi-View Clustering (AAAI 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.