Research map / Label-efficient and robust learning / Recognition and long-tail
The Benefits of Mixup for Feature Learning
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 different linear interpolation parameters for features and labels (e.g., g(lambda)=1.5-lambda, independent random lambda and g) instead of matching them (ablation) | Mixup on CIFAR-10 with ResNet18/VGG16 · CIFAR-10 without crop/flip and weight decay | test accuracy | No clear effect |
| Early stopping of Mixup (turn off Mixup after a fixed number of iterations) (ablation) | Mixup training · CIFAR-10 with crop/flip and weight decay, LeNet, VGG16, ResNet18, ResNet34 | test accuracy | Helped |
| Early stopping of Mixup at 125 iterations vs. full Mixup (ablation) | ResNet18 · CIFAR-10 without crop/flip and weight decay | test accuracy | Helped |
| Mixup training vs standard training on multi-view data model (theory) | two-layer CNN on feature-noise data · synthetic multi-view data | test error | Helped |
Closest papers by meaning
- Towards Understanding the Data Dependency of Mixup-style Training (ICLR 2022 · similarity 0.91)
- Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup (ICML 2024 · similarity 0.89)
- Pushing Boundaries: Mixup's Influence on Neural Collapse (ICLR 2024 · similarity 0.88)
- Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN (AAAI 2024 · similarity 0.87)
- For Better or For Worse? Learning Minimum Variance Features With Label Augmentation (ICLR 2025 · similarity 0.87)
- Tailoring Mixup to Data for Calibration (ICLR 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.