论文标题
基于显着地图的数据增强
Saliency Map Based Data Augmentation
论文作者
论文摘要
数据增强是一种常用技术，具有两个看似相关的优势。通过这种方法，可以增加训练集生成新样本的大小，并增加网络与应用转换的不变性。不幸的是，所有图像都包含分类的相关和无关的特征，因此该不变性必须是特定于类的。在本文中，我们将提出一种新方法，该方法使用显着图将神经网络的不变性限制为某些区域，从而在分类任务中提供了更高的测试准确性。
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.
