论文标题
对数据增强对知识蒸馏的影响的经验分析
An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
论文作者
论文摘要
通过使用数据增强策略（例如简单转换或使用混合样本），可以显着改善使用经验风险最小化训练的深度学习模型的概括性能。我们试图在蒸馏设置中经验分析此类策略对教师和学生模型之间概括的影响。我们观察到，如果使用任何混合样品增强策略（例如混音或cutmix）对教师进行了培训，则从其概括能力中却降低了学生模型。我们假设此类策略限制了模型学习特定特定特征的能力，从而导致蒸馏过程中监督信号的质量丧失。我们提出了一种新颖的类歧视度量，以定量测量这种二分法，并将其与网络潜在空间上不同策略引起的歧视能力联系起来。
Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to empirically analyze the impact of such strategies on the transfer of generalization between teacher and student models in a distillation setup. We observe that if a teacher is trained using any of the mixed sample augmentation strategies, such as MixUp or CutMix, the student model distilled from it is impaired in its generalization capabilities. We hypothesize that such strategies limit a model's capability to learn example-specific features, leading to a loss in quality of the supervision signal during distillation. We present a novel Class-Discrimination metric to quantitatively measure this dichotomy in performance and link it to the discriminative capacity induced by the different strategies on a network's latent space.
