Research map / Label-efficient and robust learning / Noisy labels
Active Label Correction Using Robust Parameter Update and Entropy Propagation
Kwang In Kim
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 |
|---|---|---|---|
| use robust contribution-weighted parameter update instead of uniform gradient combination (ablation) | active label correction · CIFAR-100 | accuracy | Improved |
| use soft robust update instead of hard noise detection [14,43] (ablation) | active label correction · CIFAR-100 | accuracy | Improved |
| add entropy diffusion to batch selection (ablation) | active label correction · Caltech-256 | accuracy | Improved |
| add entropy diffusion versus conventional batch entropy selection (pure label acquisition) (ablation) | entropy-based selection · CIFAR-100 | accuracy | Improved |
| use the proposed method instead of DALC and CorrActive | active label correction · CIFAR-10 (uniform noise) | labels to reach 90% accuracy: 9,000 / 11,000 -> 3,000 | Improved |
| use the proposed method instead of loss-based active cleaning [2] for noisy sample selection | active label correction · CIFAR-100 | noisy example selection accuracy: 91.1 -> 97.9 | Improved |
| use LossEnt selection instead of Random | LossEnt · CIFAR-10 and F-MNIST | accuracy | Hurt |
| use Entropy or CorrActive instead of Random | active label correction · benchmarks | accuracy | Improved |
| add class-transition noise model learning (DALC) to entropy selection | active label correction · benchmarks | accuracy | Improved |
Closest papers by meaning
- Meta Label Correction for Noisy Label Learning (AAAI 2021 · similarity 0.89)
- Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection (ECCV 2022 · similarity 0.88)
- Error-Bounded Correction of Noisy Labels (ICML 2020 · similarity 0.88)
- Revisiting Interpolation for Noisy Label Correction (AAAI 2025 · similarity 0.88)
- Active Label Correction for Semantic Segmentation with Foundation Models (ICML 2024 · similarity 0.87)
- Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled Yet Hard-to-Learn Samples in Noisy Data (AAAI 2025 · 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.
