Research map / Probabilistic and scientific modeling / Variational and generative sampling
A Bayesian Data Augmentation Approach for Learning Deep Models
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 Bayesian data augmentation instead of PMDA | ResNet18 · MNIST, CIFAR-10, and CIFAR-100 | top-1 classification accuracy | Helped |
| Use Bayesian data augmentation instead of PMDA | ResNetpa · MNIST, CIFAR-10, and CIFAR-100 | top-1 classification accuracy | Helped |
| Use Bayesian data augmentation instead of AC-GAN | ResNetpa · MNIST, CIFAR-10, and CIFAR-100 | top-1 classification accuracy | Helped |
| Use PMDA instead of Bayesian data augmentation during early training | ResNet18 · MNIST and CIFAR-100, early training | test classification accuracy | Helped |
| Use Bayesian data augmentation instead of PMDA after sufficient training | ResNet18 · CIFAR-100 after two hours; MNIST after five hours | test classification accuracy | Helped |
| Increase the augmented training set size (ablation) | Data augmentation methods · MNIST, CIFAR-10, and CIFAR-100 | top-1 classification accuracy | Helped |
Closest papers by meaning
- Bayesian Generative Active Deep Learning (ICML 2019 · similarity 0.89)
- Tradeoffs in Data Augmentation: An Empirical Study (ICLR 2021 · similarity 0.89)
- Data-Efficient Augmentation for Training Neural Networks (NeurIPS 2022 · similarity 0.89)
- Optimizing Data Augmentation through Bayesian Model Selection (ICLR 2026 · similarity 0.89)
- Toward Understanding Generative Data Augmentation (NeurIPS 2023 · similarity 0.88)
- Distribution Augmentation for Generative Modeling (ICML 2020 · 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.