Research map / Label-efficient and robust learning / Noisy labels
Enhancing Learning with Noisy Labels via Rockafellian Relaxation
Louis Chen, Bobbie Chern, Eric Eckstrand, Amogh Mahapatra, Johannes O. Royset
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 |
|---|---|---|---|
| wrap Divide-Mix with RRM | Divide-Mix · CIFAR-10N (Worst) | accuracy: 92.56 -> 94.75 | Improved |
| wrap Divide-Mix with RRM | Divide-Mix · CIFAR-100N (Noisy Fine) | accuracy: 71.13 -> 73.98 | Improved |
| wrap ProMix with RRM | ProMix · CIFAR-10N (Worst) | accuracy: 96.34 -> 96.32 | No clear effect |
| wrap ProMix with RRM | ProMix · CIFAR-100N (Noisy Fine) | accuracy: 73.79 -> 74.19 | Improved |
| wrap CCE with RRM | CCE · Clothing1M | accuracy: 68.94 -> 71.48 | Improved |
| wrap CC with RRM | CC · Clothing1M | accuracy: 75.4 -> 75.69 | Improved |
| wrap CCE with RRM | CCE · Food-101N | accuracy: 81.67 -> 84.21 | Improved |
| wrap CCE with RRM | CCE · CIFAR-10 symmetric noise 30% | accuracy: 81.90 -> 88.49 | Improved |
| wrap MSE with RRM | MSE · CIFAR-10 symmetric noise 30% | accuracy: 86.34 -> 89.95 | Improved |
| wrap MAE with RRM | MAE · CIFAR-10 symmetric noise | accuracy: 92.04 -> 90.10 at 10%; 83.72 -> 87.82 at 20%; 88.28 -> 82.98 at 30% | Mixed |
| add RRM reweighting to adversarial training (A-RRM vs AT) (ablation) | adversarial training with label noise · MNIST-10 20% noise, test eps 0.00 | accuracy: 58 -> 96 | Improved |
| use overestimated contamination C' = C + 10% instead of C (ablation) | RRM-wrapped MSE · CIFAR-10 symmetric noise 30% | accuracy: 89.95 -> 88.47 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- Divide-Mix — DivideMix: Learning with Noisy Labels as Semi-supervised Learning (ICLR 2020) · better on 2 of 2 shared results
- SURE — SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024) · better on 0 of 1 shared result
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
- Robust Classification via Regression for Learning with Noisy Labels (ICLR 2024 · similarity 0.89)
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization (NeurIPS 2025 · similarity 0.88)
- Rethinking Label Refurbishment: Model Robustness under Label Noise (AAAI 2023 · similarity 0.87)
- Mitigating Label Noise through Data Ambiguation (AAAI 2024 · similarity 0.86)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · similarity 0.86)
- Learning with Structural Labels for Learning with Noisy Labels (CVPR 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.
