Research map / Label-efficient and robust learning / Noisy labels
When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method
Manyi Zhang, Xuyang Zhao, Jun Yao, Chun Yuan, Weiran Huang
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 mixup to RCAL (ablation) | RCAL · CIFAR-10 (imbalance 100, noise 0.4) | test accuracy (%): 64.83 -> 69.78 | Improved |
| add representation distance regularization (REG) toward contrastive representations (ablation) | RCAL · CIFAR-10 (imbalance 100, noise 0.4) | test accuracy (%): 58.27 -> 64.83 | Improved |
| add distributional calibration (DC) with sampled Gaussian points (ablation) | RCAL · CIFAR-10 (imbalance 100, noise 0.4) | test accuracy (%): 54.61 -> 58.27 | Improved |
| add MoCo contrastive pretraining (CL) (ablation) | RCAL · CIFAR-10 (imbalance 100, noise 0.4) | test accuracy (%): 48.11 -> 54.61 | Improved |
| add contrastive learning pretraining (ablation) | RCAL · CIFAR-10 (imbalance 10, noise 0.4) | test accuracy (%): 70.13 -> 74.37 | Improved |
| change batch size from 64 to 256 (ablation) | RCAL · CIFAR-10/100 (noise 0.5) | test accuracy (%): CIFAR-10 imb 10: 79.53 -> 80.92; imb 100: 65.69 -> 63.27 | No clear effect |
| RCAL versus best baseline at high noise and imbalance | RCAL · CIFAR-10 (imbalance 100, noise 0.5) | test accuracy (%): 56.21 -> 65.05 | Improved |
| Co-teaching small-loss trick under long-tailed data | Co-teaching · CIFAR-10 (imbalance 10, noise 0.2) | test accuracy (%): 75.61 -> 78.54 vs ERM at imb 10; 62.17 -> 50.29 at imb 100 | Hurt |
| add semi-supervised learning to RCAL (RCAL+) | RCAL · WebVision-50 (WebVision val) | top-1 accuracy (%): 76.24 -> 79.56 | Improved |
| RCAL versus MiSLAS on many/medium/few classes | RCAL · CIFAR-10 (imbalance 10, noise 0.5) | overall accuracy (%): 72.46 -> 80.80 overall; few classes 81.66 -> 73.98 | Mixed |
Closest papers by meaning
- Boosting Class Representation via Semantically Related Instances for Robust Long-Tailed Learning with Noisy Labels (ICCV 2025 · similarity 0.89)
- Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition (NeurIPS 2024 · similarity 0.89)
- Balanced Contrastive Learning for Long-Tailed Visual Recognition (CVPR 2022 · similarity 0.89)
- Long-Tailed Recognition via Information-Preservable Two-Stage Learning (NeurIPS 2025 · similarity 0.88)
- Decoupled Contrastive Learning for Long-Tailed Recognition (AAAI 2024 · similarity 0.87)
- Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data (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.
