Research map / Label-efficient and robust learning / Recognition and long-tail
Class-Prior Perturbation-Robust Regularization for Imbalanced Unreliable Partial Label Learning
Congyu Qiao, Haohao Dong, Xin Geng, Ning Xu
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 class-prior perturbation-robust regularization (vs CLAPOR-N) (ablation) | CLAPOR-N · CIFAR-10 (rho=50, gamma=0.3, iota=0.3) | overall accuracy (%): 48.15 -> 61.68 | Improved |
| add class-prior perturbation-robust regularization (vs CLAPOR-N) (ablation) | CLAPOR-N · CIFAR-10 (rho=50, gamma=0.3, iota=0.3) | minority-class accuracy (%): 17.69 -> 52.40 | Improved |
| add class-prior perturbation-robust regularization (vs CLAPOR-N) (ablation) | CLAPOR-N · CIFAR-100 (rho=10, gamma=0.3, iota=0.05) | overall accuracy (%): 41.08 -> 43.14 | Improved |
| add class-prior perturbation-robust regularization (vs CLAPOR-N) (ablation) | CLAPOR-N · CIFAR-100 (rho=10, gamma=0.3, iota=0.05) | minority-class accuracy (%): 25.50 -> 30.21 | Improved |
| add class-prior perturbation-robust regularization (vs CLAPOR-N) (ablation) | CLAPOR-N · CIFAR-10 (rho=200, gamma=0.5, iota=0.3) | minority-class accuracy (%): 0.71 -> 30.53 | Improved |
| add class-prior perturbation-robust regularization (vs CLAPOR-N) (ablation) | CLAPOR-N · CIFAR-100 (rho=50, gamma=0.5, iota=0.1) | overall accuracy (%): 14.27 -> 16.90 | Improved |
| use CLAPOR instead of SOLAR | SOLAR · CIFAR-10 (rho=50, gamma=0.3, iota=0.3) | overall accuracy (%): 43.72 -> 61.68 | Improved |
| use CLAPOR instead of PICO | PICO · CIFAR-10 (rho=50, gamma=0.3, iota=0.3) | minority-class accuracy (%): 27.12 -> 52.40 | Improved |
| use CLAPOR instead of ALIM | ALIM · CIFAR-10 (minority, all settings) | minority-class accuracy (%) | No clear effect |
| vary mu in 0.1-0.9, lambda in 10-50, beta in 1-5 (ablation) | CLAPOR · CIFAR-10 (rho=50, gamma=0.3, iota=0.3) | overall and minority accuracy | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PICO — PiCO: Contrastive Label Disambiguation for Partial Label Learning (ICLR 2022) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ConR: Contrastive Regularizer for Deep Imbalanced Regression (ICLR 2024 · similarity 0.88)
- AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions (NeurIPS 2026 · similarity 0.88)
- Controller-Guided Partial Label Consistency Regularization with Unlabeled Data (AAAI 2024 · similarity 0.87)
- Rebalancing Multi-Label Class-Incremental Learning (AAAI 2025 · similarity 0.86)
- Twice Class Bias Correction for Imbalanced Semi-supervised Learning (AAAI 2024 · similarity 0.86)
- Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise (AAAI 2024 · similarity 0.86)
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.
