Research map / Label-efficient and robust learning / Noisy labels
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
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 |
|---|---|---|---|
| train with L_DMI instead of cross entropy | ResNet-50 · Clothing1M | test accuracy: 68.94 -> 72.46 | Helped |
| L_DMI vs LCCN | ResNet-50 · Clothing1M | test accuracy: 71.63 -> 72.46 | Helped |
| L_DMI instead of CE under non-diagonally dominant noise | two-layer CNN · Fashion-MNIST (binary, imbalanced) | test accuracy | Helped |
| L_DMI instead of CE under diagonally dominant noise | two-layer CNN · Fashion-MNIST (binary, imbalanced) | test accuracy | No clear effect |
| L_DMI vs GCE on clean data | classifiers · CIFAR-10, Dogs vs. Cats, MR | test accuracy | Hurt |
| L_DMI vs FW, GCE, LCCN under increasing synthetic noise | ResNet-34/VGG-16/WordCNN · CIFAR-10, Dogs vs. Cats, MR | test accuracy | Helped |
Closest papers by meaning
- Robust Loss Functions under Label Noise for Deep Neural Networks (AAAI 2017 · similarity 0.91)
- Normalized Loss Functions for Deep Learning with Noisy Labels (ICML 2020 · similarity 0.91)
- Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning (AAAI 2025 · similarity 0.90)
- $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise (NeurIPS 2024 · similarity 0.89)
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization (NeurIPS 2025 · similarity 0.88)
- Learning with Structural Labels for Learning with Noisy Labels (CVPR 2024 · similarity 0.88)
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.