A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
This incremental work provides practical guidelines for researchers and practitioners in computer vision to improve deep learning model training with limited data.
The study investigated how data augmentation variables—method, rate, and dataset size—affect image classification accuracy, finding that geometric transformations are better than lighting/color changes, a 2-3 times augmentation rate is optimal, and benefits are more pronounced with smaller datasets.
Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is expensive in practice. Data augmentation is one of themethods to alleviate this problem. In this paper, we conduct apreliminary study on how three variables (augmentation method,augmentation rate and size of basic dataset per label) can affectthe accuracy of deep learning for image classification. The studyprovides some guidelines: (1) it is better to use transformationsthat alter the geometry of the images rather than those justlighting and color. (2) 2-3 times augmentation rate is good enoughfor training. (3) the smaller amount of data, the more obviouscontributions could have.