Research map / Label-efficient and robust learning / Recognition and long-tail
Information Bottleneck Learning Using Privileged Information for Visual Recognition
Check 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 |
|---|---|---|---|
| Use auxiliary HOG features during training | LMIBPI · HMDB action recognition | accuracy | Helped |
| Use auxiliary bounding-box-region features during training | LMIBPI · ImageNet snake classification | accuracy | Helped |
| Use auxiliary joint-position histograms during training | LMIBPI · CGD2011 gesture recognition | accuracy | Helped |
| Use auxiliary animal attributes during training | LMIBPI · AwA one-vs-one classification | average precision: 20 times out of 45 | Mixed |
| Add auxiliary information rather than set γ = 0 (ablation) | LMIBPI · HMDB, punch | accuracy: 83.76 ± 3.20 -> 92.06 ± 3.54 | Helped |
Closest papers by meaning
- Structured IB: Improving Information Bottleneck with Structured Feature Learning (AAAI 2025 · similarity 0.84)
- Decoupled Optimisation for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.84)
- Feature Fusion from Head to Tail for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.84)
- Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers (CVPR 2025 · similarity 0.84)
- Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data (AAAI 2024 · similarity 0.83)
- LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision (NeurIPS 2025 · similarity 0.83)
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.