Saliency Map Based Data Augmentation
This addresses the need for more effective data augmentation in image classification, though it appears incremental as it builds on existing saliency map techniques.
The paper tackles the problem of class-specific invariance in data augmentation by using saliency maps to restrict transformations to relevant image regions, resulting in higher test accuracy in classification tasks.
Data augmentation is a commonly applied technique with two seemingly related advantages. With this method one can increase the size of the training set generating new samples and also increase the invariance of the network against the applied transformations. Unfortunately all images contain both relevant and irrelevant features for classification therefore this invariance has to be class specific. In this paper we will present a new method which uses saliency maps to restrict the invariance of neural networks to certain regions, providing higher test accuracy in classification tasks.