Research map / Label-efficient and robust learning / Recognition and long-tail
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
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 Midpoint Mixup instead of ERM | ResNet-18 · FMNIST unmodified test data | test error: 16.55 ± 2 -> 14.84 ± 1 | Helped |
| Use Midpoint Mixup instead of Uniform Mixup | ResNet-18 · FMNIST unmodified test data | test error: 9.66 -> 14.84 ± 1 | Hurt |
| Use Midpoint Mixup instead of ERM | ResNet-18 · CIFAR-10 unmodified test data | test error: 27.77 ± 2 -> 22.29 ± 2 | Helped |
| Use Midpoint Mixup instead of Uniform Mixup | ResNet-18 · CIFAR-10 unmodified test data | test error: 18.52 ± 1 -> 22.29 ± 2 | Hurt |
| Use Midpoint Mixup instead of ERM | ResNet-18 · CIFAR-100 unmodified test data | test error: 69.28 ± 2 -> 53.61 ± 2 | Helped |
| Use Midpoint Mixup instead of Uniform Mixup | ResNet-18 · CIFAR-100 unmodified test data | test error: 53.42 ± 1 -> 53.61 ± 2 | No clear effect |
| Train with Midpoint Mixup rather than ERM | 2-layer CNN on general multi-view data · Theoretical multi-view data distribution | classes learning both features | Helped |
Closest papers by meaning
- On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks (NeurIPS 2019 · similarity 0.88)
- Noisy Feature Mixup (ICLR 2022 · similarity 0.88)
- Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN (AAAI 2024 · similarity 0.88)
- Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup (ICML 2024 · similarity 0.86)
- Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model (CVPR 2024 · similarity 0.86)
- Adversarial AutoMixup (ICLR 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.