Research map / Label-efficient and robust learning / Recognition and long-tail
Conformal Prediction Meets Long-tail Classification
Shuqi Liu, Jianguo Huang, Luke Ong
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 selective rank regularization on head classes (TACP) to standard CP | APS score · ImageNet-LT rho=0.6 | head-tail coverage gap CovGap-HT (%): 2.18 -> 1.11 | Improved |
| apply TACP to TOPK score | TOPK · ImageNet-LT rho=0.6 | head-tail coverage gap CovGap-HT (%): 8.83 -> 1.02 | Improved |
| apply TACP to TOPK score | TOPK · ImageNet-LT rho=0.6 | average set size: 23.15 -> 25.63 | Hurt |
| apply TACP instead of STANDARD (APS) | APS · CIFAR100-LT mu=100 | head-tail coverage gap CovGap-HT (%): 4.81 -> 0.78 | Improved |
| TACP vs Partition-Wise calibration | LAC · ImageNet-LT rho=0.6 | head-tail coverage gap CovGap-HT (%): 1.96 -> 1.18 | Improved |
| replace hard head indicator with soft class-prior weighting (sTACP) | APS · ImageNet-LT rho=0.6 (alpha=10%) | class-conditional coverage gap CovGap (%): 19.00 -> 15.86 | Improved |
| use sTACP instead of ClassWise | APS · ImageNet-LT rho=0.6 (alpha=5%) | set size: 983.53 -> 76.83 | Improved |
| use sTACP at alpha=5% vs STANDARD | APS · ImageNet-LT rho=0.6 (alpha=5%) | class-conditional coverage gap CovGap (%): 9.62 -> 8.08 | Improved |
| use sTACP instead of STANDARD at alpha=5% on set size | APS · ImageNet-LT rho=0.6 (alpha=5%) | average set size: 67.49 -> 76.83 | Hurt |
Closest papers by meaning
- Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration (NeurIPS 2024 · similarity 0.90)
- Reliable Uncertainty Quantification in Machine Learning via Conformal Prediction (AAAI 2025 · similarity 0.89)
- Optimal transport-based conformal prediction (ICML 2025 · similarity 0.89)
- Verifiably Robust Conformal Prediction (NeurIPS 2024 · similarity 0.88)
- Hierarchical Conformal Classification (NeurIPS 2026 · similarity 0.88)
- CBMA: Improving Conformal Prediction through Bayesian Model Averaging (ICLR 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.
