Research map / Label-efficient and robust learning / Noisy labels
Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels
Wenxiao Fan, Kan Li
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 SNOP (ablation) | RoLR + NegScale · CIFAR-100 Sym 80% | accuracy: 67.2 -> 70.8 | Improved |
| add SNOP (ablation) | RoLR + NegScale · CIFAR-10 Sym 50% | accuracy: 95.1 -> 96.6 | Improved |
| add DCSA (ablation) | RoLR + NegScale · CIFAR-100 Sym 80% | accuracy: 68.1 -> 70.8 | Improved |
| add DCSA (ablation) | RoLR + NegScale · CIFAR-10 Sym 80% | accuracy: 94.8 -> 95.6 | Improved |
| select negatives by pLCA structure instead of random selection (ablation) | RoLR + NegScale · CIFAR-100 Sym 80% | accuracy: 65.2 -> 70.8 | Improved |
| select negatives by pLCA structure instead of random selection (ablation) | RoLR + NegScale · CIFAR-10 Sym 50% | accuracy: 94.1 -> 96.6 | Improved |
| add NegScale to DivideMix | DivideMix · CIFAR-100 Sym 80% | accuracy: 59.6 -> 70.3 | Improved |
| add NegScale to DivideMix | DivideMix · CIFAR-10 Sym 80% | accuracy: 92.9 -> 94.6 | Improved |
| add NegScale to RankMatch | RankMatch · CIFAR-100 Sym 80% | accuracy: 67.2 -> 70.8 | Improved |
| add NegScale to ANNE | ANNE · CIFAR-100 Sym 80% | accuracy: 73.0 -> 73.5 | Improved |
| add NegScale to ANNE | ANNE · CIFAR-10 Sym 80% | accuracy: 95.3 -> 96.2 | Improved |
| add NegScale to RoLR | RoLR · CIFAR-100 Sym 80% | accuracy: 66.2 -> 70.8 | 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.
- RankMatch — RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels (ICCV 2023) · better on 1 of 1 shared result
- DivideMix — DivideMix: Learning with Noisy Labels as Semi-supervised Learning (ICLR 2020) · 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
- Stabilizing Sample Similarity in Representation via Mitigating Random Consistency (ICML 2025 · similarity 0.86)
- NoiseGPT: Label Noise Detection and Rectification through Probability Curvature (NeurIPS 2024 · similarity 0.85)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.85)
- Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation (NeurIPS 2025 · similarity 0.84)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.84)
- Revisiting Interpolation for Noisy Label Correction (AAAI 2025 · similarity 0.84)
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.
