Research map / Label-efficient and robust learning / Noisy labels
Foster Adaptivity and Balance in Learning with Noisy Labels
Mengmeng Sheng, Zeren Sun, Tao Chen, Shuchao Pang, yucheng wang, Yazhou Yao
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 self-adaptive class-balanced sample selection (SCS) to standard training (ablation) | Standard training · CIFAR100N Sym-50% | test accuracy (%): 34.10 -> 58.21 | Improved |
| add local (class-specific) thresholds to SCS (ablation) | SCS · CIFAR100N Sym-50% | test accuracy (%): 53.36 -> 58.21 | Improved |
| add global threshold to SCS (ablation) | SCS · CIFAR100N Sym-50% | test accuracy (%): 55.64 -> 58.21 | Improved |
| add EMA to threshold estimation (ablation) | SCS · CIFAR100N Sym-50% | test accuracy (%): 54.72 -> 58.21 | Improved |
| add self-adaptive class-balanced re-weighting (SCR) (ablation) | Standard+SCS · CIFAR100N Sym-50% | test accuracy (%): 58.21 -> 60.43 | Improved |
| add confidence-based re-weighting inside SCR (ablation) | Standard+SCS+SCR · CIFAR100N Sym-50% | test accuracy (%): 59.75 -> 60.43 | Improved |
| add consistency regularization on clean samples (ablation) | Standard+SCS+SCR · CIFAR100N Sym-50% | test accuracy (%): 60.43 -> 62.65 | Improved |
| add class-balanced design (ablation) | SED · CIFAR100N Asym-40% | test accuracy (%): 52.78 -> 58.80 | Improved |
| add class-balanced design (ablation) | SED · CIFAR100N Sym-80% | test accuracy (%): 38.08 -> 39.32 | Improved |
| use SED instead of DISC (best prior) | noisy label learning · Web-Aircraft/Bird/Car average | test accuracy (%): 84.89 -> 85.83 | Improved |
| use SED instead of Co-LDL | noisy label learning · CIFAR100N Asym-40% | test accuracy (%): 52.28 -> 58.29 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- UNICON — UniCon: Combating Label Noise Through Uniform Selection and Contrastive Learning (CVPR 2022) · better on 1 of 1 shared result
- Jo-SRC — Jo-SRC: A Contrastive Approach for Combating Noisy Labels (CVPR 2021) · better on 1 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
- Uncertainty-Aware Learning against Label Noise on Imbalanced Datasets (AAAI 2022 · similarity 0.90)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · similarity 0.89)
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization (NeurIPS 2025 · similarity 0.88)
- Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise (AAAI 2024 · similarity 0.88)
- Revisiting Interpolation for Noisy Label Correction (AAAI 2025 · similarity 0.88)
- Learning Imbalanced Data with Beneficial Label Noise (ICML 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.
