Research map / Label-efficient and robust learning / Noisy labels
Provably End-to-end Label-noise Learning without Anchor Points
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use VolMinNet instead of the strongest reported baseline | label-noise classification · Synthetic datasets, symmetric and pair-flipping noise | accuracy | Helped |
| Use VolMinNet instead of the strongest reported baseline | CIFAR-10 classification · CIFAR-10 Pair-45% | accuracy: 78.94 ± 2.58 -> 88.54 ± 0.21 | Helped |
| Use VolMinNet instead of the strongest reported baseline | CIFAR-100 classification · CIFAR-100 Pair-45% | accuracy: 47.60 ± 0.43 -> 58.90 ± 0.89 | Helped |
| Use VolMinNet instead of PTD | Clothing1M classification using noisy data only · Clothing1M | accuracy: 71.67 -> 72.42 | Helped |
| Estimate the transition matrix with minimum-volume simplex regularization rather than the compared estimators | transition matrix estimation · CIFAR-100 Flip-0.45 | transition matrix estimation error: around 0.75 -> around 0.25 | Helped |
| Use VolMinNet when possible anchor points have been removed | label-noise classification · MNIST/NA, CIFAR-10/NA, and CIFAR-100/NA | accuracy | Helped |
Closest papers by meaning
- Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification (NeurIPS 2026 · similarity 0.91)
- Learning the Latent Causal Structure for Modeling Label Noise (NeurIPS 2024 · similarity 0.88)
- Learning Causal Transition Matrix for Instance-dependent Label Noise (AAAI 2025 · similarity 0.88)
- Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning (CVPR 2024 · similarity 0.87)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · similarity 0.87)
- Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning (ICLR 2024 · similarity 0.87)
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.