|
|
--- |
|
|
license: mit |
|
|
library_name: pytorch |
|
|
tags: |
|
|
- image-classification |
|
|
- data-augmentation |
|
|
- small-sample-learning |
|
|
- empirical-study |
|
|
- rethinking |
|
|
datasets: |
|
|
- cifar100 |
|
|
- cifar10 |
|
|
metrics: |
|
|
- accuracy |
|
|
--- |
|
|
|
|
|
# Rethinking Augmentation: Experiment Results |
|
|
# 小样本增强策略再思考：实验结果库 |
|
|
|
|
|
Official experiment results repository for the paper: |
|
|
**"When More is Not Better: Rethinking Data Augmentation under Small-Sample Regimes"** |
|
|
|
|
|
**TL;DR**: We find that in small-sample regimes (e.g., CIFAR-100 100-shot), complex augmentation strategies (like RandAugment) often yield diminishing returns and high instability. A single, well-tuned operation can achieve comparable accuracy with significantly lower variance. |
|
|
|
|
|
**核心发现**：在小样本场景下，盲目增加数据增强的复杂度（如 RandAugment）往往收益递减且带来极大的不稳定性。我们发现，单一且经过调优的增强操作能在保持精度的同时显著降低方差。 |
|
|
|
|
|
--- |
|
|
|
|
|
## 📊 Key Findings / 核心发现 |
|
|
|
|
|
### 1. Stability-Accuracy Trade-off / 稳定性与精度的权衡 (CIFAR-100 100-shot) |
|
|
| Policy / 策略 | Val Acc (%) | Stability (Std) | Note | |
|
|
| :--- | :--- | :--- | :--- | |
|
|
| **RandAugment** (N=2,M=9) | 42.24% | 1.17 | High Variance (Unstable) | |
|
|
| **Single-Op** (Ours) | 40.74% | **0.78** (Lowest) | **Stable & Reliable** | |
|
|
| **Baseline** | 39.90% | 1.01 | - | |
|
|
|
|
|
### 2. Zero-Variance Generalization / 零方差泛化 (CIFAR-10 50-shot) |
|
|
| Metric / 指标 | Result / 结果 | |
|
|
| :--- | :--- | |
|
|
| **Top-1 Accuracy** | 50.0% | |
|
|
| **Stability (Std)** | **0.0** (Zero Variance across 3 seeds) | |
|
|
|
|
|
--- |
|
|
|
|
|
## 📂 Repository Structure / 仓库结构 |
|
|
|
|
|
- `checkpoints/`: PyTorch model weights (`best_model.pth`). / 官方模型权重。 |
|
|
- `figures/`: Paper visualizations (Heatmaps, Trade-off plots). / 论文可视化图表（热图、权衡对比图等）。 |
|
|
- [phase_c_final_policy.json](phase_c_final_policy.json): The discovered optimal single-operation policy. / 搜索出的最优单一增强策略。 |
|
|
- [cifar10_50shot_results.csv](cifar10_50shot_results.csv): CIFAR-10 generalization experiment data. / CIFAR-10 泛化实验数据。 |
|
|
- [stability_seeds_results.csv](stability_seeds_results.csv): Raw data verifying the stability claim. / 验证“稳定性”结论的原始数据。 |
|
|
- [destructiveness_metrics.csv](destructiveness_metrics.csv): LPIPS/SSIM analysis for semantic preservation. / 语义保真度分析数据。 |
|
|
|
|
|
--- |
|
|
|
|
|
## 📜 Citation / 引用 |
|
|
If you find this study useful, please cite our work: |
|
|
如果您觉得这项研究对您有启发，请引用我们的工作： |
|
|
|
|
|
*(Citation will be updated upon acceptance / 论文接收后更新)* |
|
|
|
|
|
--- |
|
|
|
|
|
## 🔗 Links / 相关链接 |
|
|
- **Code & Paper**: [imnotnoahhh/Rethinking-Augmentation](https://github.com/imnotnoahhh/Rethinking-Augmentation) |
