An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
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...
Saved in:
Main Authors | , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
06.06.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | 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. |
---|---|
DOI: | 10.48550/arxiv.2006.03810 |