Research map / Architectures and efficiency / Neural architecture search
Improving Auto-Augment via Augmentation-Wise Weight Sharing
Keyu Tian, Chen Lin, Ming Sun, Luping Zhou, Junjie Yan, Wanli Ouyang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 AWS-searched augmentation instead of the baseline preprocessing | PyramidNet on CIFAR-10 · CIFAR-10 | top-1 test error (%): 2.67 -> 1.24 | Improved |
| use AWS-searched augmentation instead of the baseline preprocessing | WRN on CIFAR-100 · CIFAR-100 | top-1 test error (%): 18.80 -> 14.16 | Improved |
| use AWS-searched augmentation instead of the baseline preprocessing | ResNet-50 on ImageNet · ImageNet | top-1 test error (%): 23.7 -> 20.36 | Improved |
| use 4× enlarged batch with AWS (ablation) | ResNet-50 with AWS · ImageNet | top-1 test error (%): 20.61 ± 0.17 -> 20.36 ± 0.15 | Improved |
| use augmentation-trained shared weights rather than weights trained without augmentation (ablation) | AWS proxy P_AF · CIFAR-10 | Pearson correlation: 0.55 -> 0.85 | Improved |
| use learned shared weights rather than random initialization (ablation) | AWS proxy P_AF · CIFAR-10 | Pearson correlation: 0.36 -> 0.85 | Improved |
| fine-tune shared weights before evaluating the policy (ablation) | AWS proxy P_AF · CIFAR-10 | Pearson correlation: 0.045 -> 0.85 | Improved |
| apply augmentation during later rather than early training epochs (ablation) | ResNet-18 · CIFAR-10 | model performance | Improved |
| use AWS instead of AutoAugment for policy search | augmentation search on CIFAR-10 · CIFAR-10 | relative time consuming (times): 60 -> 1.5 | Improved |
Closest papers by meaning
- Faster AutoAugment: Learning Augmentation Strategies Using Backpropagation (ECCV 2020 · similarity 0.89)
- AutoAugment: Learning Augmentation Strategies From Data (CVPR 2019 · similarity 0.88)
- Scale-Aware Automatic Augmentations for Object Detection With Dynamic Training (TPAMI 2022 · similarity 0.87)
- Online Hyper-Parameter Learning for Auto-Augmentation Strategy (ICCV 2019 · similarity 0.87)
- RandAugment: Practical Automated Data Augmentation with a Reduced Search Space (NeurIPS 2020 · similarity 0.86)
- UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation (NeurIPS 2025 · similarity 0.84)
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.
