复现研究：纯噪声图像可提升少数类分类准确率
[Re] Pure Noise to the Rescue of Insufficient Data
有人把 2021 年那篇用纯噪声补少数类样本的论文复现了一遍，四个结论全复现成功，还发现它和加大网络的效果是互补的，做分类不平衡数据可以参考。
这项复现研究检验了 Zada、Benou 和 Irani 2021 年论文 Pure Noise to the Rescue of Insufficient Data 的四个主要结论。研究者用 PyTorch 重新实现训练流程，复现了纯噪声过采样（OPeN）能提升少数类准确率的结论。配套的批归一化方法（用自然图像学习的仿射参数归一化噪声图像）也确认优于基线，且改进在不同数据增强强度下保持稳定。结论 (iv) 同样成立：在均衡训练集上加入纯噪声图像也能提升分类效果。补充实验发现 OPeN 带来的提升与更大网络或更复杂数据增强带来的提升可能相互正交。
[Re] Pure Noise to the Rescue of Insufficient Data
We examine the main claims of Zada, Benou, and Irani (2021), which states that in an image classification task with imbalanced training data, (i) using pure noise to augment minority-class images encourages generalization by improving minority-class accuracy. This method is paired with (ii) a new batch normalization layer that normalizes noise images using affine parameters learned from natural images, which improves the model's performance. Moreover, (iii) this improvement is robust to varying levels of data augmentation. Finally, the authors propose that (iv) adding pure noise images can improve classification even on balanced training data. We implemented the training pipeline from the description of the paper using PyTorch and integrated authors' code snippets for sampling pure noise images and batch normalizing noise and natural images separately. We reproduced the main claims that (i) oversampling with pure noise improves generalization by improving the minority-class accuracy, (ii) the proposed batch normalization (BN) method outperforms baselines, (iii) and this improvement is robust across data augmentations. Our results also support that (iv) adding pure noise images can improve classification on balanced training data. However, additional experiments suggest that the performance improvement from OPeN may be more orthogonal to the improvement caused by a bigger network or more complex data augmentation.