Research map / Label-efficient and robust learning / Noisy labels
ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning
Mingyu Xu, Zheng Lian, Lei Feng, Bin Liu, Jianhua Tao
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 ALIM label-importance weighting to PiCO with Onehot normalization | PiCO · CIFAR-10 (q=0.3, η=0.3) | accuracy: 92.94±0.24 -> 94.67±0.21 | Improved |
| Add ALIM label-importance weighting to PiCO with Scale normalization | PiCO · CIFAR-100 (q=0.03, η=0.3) | accuracy: 69.97±0.01 -> 75.92±0.14 | Improved |
| Add ALIM-Scale to PiCO+ with mixup | PiCO · CUB-200 (q=0.05, η=0.2) | accuracy: 60.65±0.79 -> 68.38±0.47 | Improved |
| Add ALIM-Scale to PiCO+ with mixup | PiCO · CIFAR-100 (q=0.05, η=0.5) | accuracy: 60.50±0.99 -> 72.26±0.25 | Improved |
| Add mixup training to ALIM-Onehot (ablation) | ALIM-Onehot on PiCO · CIFAR-10 (q=0.3, η=0.3) | accuracy: 92.42±0.17 -> 94.67±0.21 | Improved |
| Add mixup training to ALIM-Scale (ablation) | ALIM-Scale on PiCO · CIFAR-100 (q=0.03, η=0.3) | accuracy: 71.69±0.39 -> 75.92±0.14 | Improved |
| Use Onehot instead of Scale normalization (ablation) | ALIM on PiCO · CIFAR-10 (q=0.3, η=0.3) | accuracy: 92.01±0.19 -> 92.42±0.17 | Improved |
| Use Onehot instead of Scale normalization (ablation) | ALIM on PiCO · CIFAR-100 (q=0.03, η=0.3) | accuracy: 71.69±0.39 -> 70.14±0.25 | Hurt |
| Use the adaptively adjusted λ instead of manually selected λ (ablation) | ALIM · CIFAR-10 and CIFAR-100 | accuracy | No clear effect |
| Add ALIM to RC | RC · CIFAR-10 and CIFAR-100 under noisy conditions | accuracy: 80.87±0.30 -> 88.81±0.17 | Improved |
| Add ALIM to CRDPLL | CRDPLL · CIFAR-10 under noisy conditions | accuracy: 93.48±0.17 -> 96.03±0.23 | Improved |
| Increase warm-up duration (ablation) | ALIM · CIFAR-10 and CIFAR-100 | accuracy | Mixed |
Closest papers by meaning
- Conformal Prediction for Partial Label Learning (AAAI 2025 · similarity 0.88)
- Realistic Evaluation of Deep Partial-Label Learning Algorithms (ICLR 2025 · similarity 0.87)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.87)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · similarity 0.86)
- Mitigating Label Noise through Data Ambiguation (AAAI 2024 · similarity 0.86)
- Does Label Smoothing Help Deep Partial Label Learning? (ICML 2024 · similarity 0.85)
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.
