Research map / Label-efficient and robust learning / Noisy labels
Masking: A New Perspective of Noisy Supervision
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 MASKING with a human-provided structure prior rather than S-adaptation | Noisy-label classifier · Clothing1M test | accuracy (%): 70.3 -> 71.1 | Helped |
| Use MASKING with a human-provided structure prior rather than F-correction | Noisy-label classifier · Clothing1M test | accuracy (%): 69.8 -> 71.1 | Helped |
| Use MASKING rather than training directly on noisy data | Noisy-label classifier · Clothing1M test | accuracy (%): 68.9 -> 71.1 | Helped |
| Use a structure prior in MASKING rather than unconstrained noise-transition estimation | CIFAR-10 and CIFAR-100 benchmark experiments · CIFAR-10 and CIFAR-100, column-diagonal, tri-diagonal, and block-diagonal noise | test accuracy | Helped |
Closest papers by meaning
- Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization (ICML 2021 · similarity 0.89)
- Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels (ICML 2021 · similarity 0.88)
- Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning (CVPR 2024 · similarity 0.87)
- Learning the Latent Causal Structure for Modeling Label Noise (NeurIPS 2024 · similarity 0.86)
- An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations (NeurIPS 2025 · similarity 0.86)
- Label Noise: Ignorance Is Bliss (NeurIPS 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.