Research map / Label-efficient and robust learning / Recognition and long-tail
Long-Tailed Partial Label Learning via Dynamic Rebalancing
Feng Hong, Jiangchao Yao, Zhihan Zhou, Ya Zhang, Yanfeng 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 RECORDS dynamic rebalancing | CORR · CIFAR-10-LT (ρ=50, q=0.3) | Top-1 accuracy: 76.12 -> 82.57 | Improved |
| Add RECORDS dynamic rebalancing | CORR · CIFAR-10-LT (ρ=100, q=0.7) | Top-1 accuracy: 38.11 -> 57.46 | Improved |
| Add RECORDS dynamic rebalancing | CORR · CIFAR-100-LT (ρ=50, q=0.03) | Top-1 accuracy: 42.29 -> 48.06 | Improved |
| Add RECORDS dynamic rebalancing | CORR · CIFAR-100-LT (ρ=100, q=0.07) | Top-1 accuracy: 31.05 -> 38.65 | Improved |
| Add RECORDS dynamic rebalancing | CORR · PASCAL VOC | Top-1 accuracy: 24.43 -> 56.46 | Improved |
| Apply oracle logit adjustment during training | CORR · CIFAR-10-LT (ρ=50, q=0.3) | Top-1 accuracy: 76.12 -> 36.27 | Hurt |
| Apply oracle logit adjustment during training | CORR · PASCAL VOC | Top-1 accuracy: 24.43 -> 52.51 | Improved |
| Replace RECORDS with temperature-scaled oracle logit adjustment (ablation) | CORR · CIFAR-100-LT (ρ=100, q=0.05) | Top-1 accuracy: 34.09 -> 43.46 | Hurt |
| Estimate the class distribution from the latest epoch's predictions instead of momentum-updated batch features (ablation) | CORR + RECORDS · CIFAR-100-LT (ρ=100, q=0.05) | Top-1 accuracy: 37.14 vs. 40.59 | Hurt |
| Set momentum coefficient m to 1.0, eliminating prototype updates (ablation) | CORR + RECORDS · LT-PLL benchmarks | Top-1 accuracy | Hurt |
| Vary momentum coefficient m from the reported best value (ablation) | CORR + RECORDS · CIFAR-100-LT (ρ=100, q=0.05) | Top-1 accuracy | Hurt |
Closest papers by meaning
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
- Long-Tailed Partial Label Learning by Head Classifier and Tail Classifier Cooperation (AAAI 2024 · similarity 0.89)
- Rebalancing Multi-Label Class-Incremental Learning (AAAI 2025 · similarity 0.88)
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.88)
- Long-tailed Recognition with Model Rebalancing (NeurIPS 2025 · similarity 0.88)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · similarity 0.88)
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.
