论文标题
亲和力与多样性：量化数据扩展的机制
Affinity and Diversity: Quantifying Mechanisms of Data Augmentation
论文作者
论文摘要
尽管数据增强已成为深神经网络训练的标准组成部分，但这些技术有效性背后的基本机制仍然很少了解。实际上，通常使用分配转移或增强多样性的启发式方法选择增强政策。受这些启发，我们试图量化数据增强如何改善模型的概括。为此，我们引入了可解释且易于计算的措施：亲和力和多样性。我们发现，不仅可以共同优化两者，因此预测了增强性能。
Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen using heuristics of either distribution shift or augmentation diversity. Inspired by these, we seek to quantify how data augmentation improves model generalization. To this end, we introduce interpretable and easy-to-compute measures: Affinity and Diversity. We find that augmentation performance is predicted not by either of these alone but by jointly optimizing the two.
