Research map / Label-efficient and robust learning / Recognition and long-tail
GUIDE: Gated Uncertainty-Informed Disentangled Experts for Long-tailed Recognition
Yuan Dong, Zhe Zhao, Liheng Yu, Di Wu, Pengkun Wang
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 Level 1 competitive specialization (feature decorrelation + JSD) (ablation) | entangled multi-expert baseline · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 45.8 -> 50.4 | Improved |
| add Level 2 uncertainty-guided expert refinement (ablation) | entangled multi-expert baseline · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 45.8 -> 51.3 | Improved |
| add Level 3 two-timescale updates (ablation) | entangled multi-expert baseline · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 45.8 -> 49.9 | Improved |
| add Level 2 on top of Level 1 (ablation) | GUIDE Level 1 · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 50.4 -> 52.8 | Improved |
| add Level 3 on top of Levels 1 and 2 (ablation) | GUIDE Level 1+2 · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 52.8 -> 56.4 | Improved |
| add only the feature decorrelation loss (ablation) | entangled baseline · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 45.8 -> 47.7 | Improved |
| add only the JSD prediction divergence loss (ablation) | entangled baseline · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 45.8 -> 47.5 | Improved |
| combine both diversity losses (ablation) | entangled baseline · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 45.8 -> 50.4 | Improved |
| use epistemic/aleatoric decomposed gating instead of total uncertainty (ablation) | GUIDE DERM gating · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 54.9 -> 56.4 | Improved |
| use decomposed uncertainty gating instead of inverse-frequency static gate (ablation) | GUIDE DERM gating · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 53.6 -> 56.4 | Improved |
| use adaptive gating instead of fixed gate 0.5 (ablation) | GUIDE DERM gating · CIFAR-100-LT IR=100 (standard schedule) | overall top-1 accuracy (%): 52.1 -> 56.4 | Improved |
| increase experts from one to three (ablation) | GUIDE · CIFAR-100-LT IR=100 (standard schedule) | few-shot accuracy: 10.9% absolute gain | Improved |
Closest papers by meaning
- MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition (ICCV 2023 · similarity 0.88)
- Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks (NeurIPS 2024 · similarity 0.86)
- DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge (NeurIPS 2024 · similarity 0.86)
- Long-tailed Recognition with Model Rebalancing (NeurIPS 2025 · similarity 0.86)
- $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity (ICLR 2024 · similarity 0.85)
- Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer (ICLR 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.
