Research map / Label-efficient and robust learning / Noisy labels
Multi-Objective Interpolation Training for Robustness To Label Noise
Check 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 |
|---|---|---|---|
| Add interpolated contrastive learning instead of supervised contrastive learning | CIFAR-100 representation learning · CIFAR-100 symmetric noise 40% | weighted k-NN accuracy: 58.32 -> 66.38 | Helped |
| Add the classification objective alongside ICL | CIFAR-100 representation learning · CIFAR-100 symmetric noise 40% | weighted k-NN accuracy: 66.38 -> 67.42 | Helped |
| Use corrected neighborhood soft-labels instead of uncorrected soft-labels for detection | MOIT · CIFAR-100 asymmetric noise 40% | accuracy: 67.68 -> 71.42 | Helped |
| Balance the detected clean set using the median criterion (ablation) | MOIT · CIFAR-100 asymmetric noise 40% | accuracy: 69.58 -> 71.42 | Helped |
| Add semi-supervised learning (ablation) | MOIT · CIFAR-100 symmetric noise 40% | accuracy: 62.82 -> 66.58 | Helped |
| Add a memory bank (ablation) | MOIT · CIFAR-100 symmetric noise 40% | accuracy: 66.10 -> 66.58 | Helped |
| Add classifier retraining during refinement (ablation) | MOIT+ · CIFAR-100 symmetric noise 40% | accuracy: 69.54 -> 70.68 | Helped |
| Avoid strong data augmentation during MOIT+ refinement (ablation) | MOIT+ · CIFAR-100 symmetric noise 40% | accuracy: 67.98 -> 70.68 | Helped |
| Add the MOIT+ clean-data refinement stage | MOIT · mini-WebVision | Best accuracy: 78.36 -> 78.76 | Helped |
| Add the MOIT+ clean-data refinement stage | MOIT · CIFAR-10 synthetic noise (Avg.) | accuracy: 89.73 -> 91.33 | Helped |
Closest papers by meaning
- On Learning Contrastive Representations for Learning With Noisy Labels (CVPR 2022 · similarity 0.89)
- Revisiting Interpolation for Noisy Label Correction (AAAI 2025 · similarity 0.88)
- On the Role of Label Noise in the Feature Learning Process (ICML 2025 · similarity 0.87)
- NoiseGPT: Label Noise Detection and Rectification through Probability Curvature (NeurIPS 2024 · similarity 0.87)
- Mitigating Label Noise through Data Ambiguation (AAAI 2024 · similarity 0.87)
- IOFM: Using the Interpolation Technique on the Over-Fitted Models to Identify Clean-Annotated Samples (AAAI 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.