The Grad-CAM algorithm provides a way to identify what parts of an image contribute most to the output of a classifier deep network. The algorithm is simple and widely used for localization of objects in an image, although some researchers have point out its limitations, and proposed various alternatives. One of them is Grad-CAM++, that according to its authors can provide better visual explanations for network predictions, and does a better job at locating objects even for occurrences of multiple object instances in a single image. Here we show that Grad-CAM++ is practically equivalent to a very simple variation of Grad-CAM in which gradients are replaced with positive gradients.

翻译：Grad- CAM 算法提供了一种方法来确定图像中哪些部分对分类器深度网络的产出贡献最大。 算法简单而广泛, 用于图像中对象的定位, 尽管有些研究人员已经指出其局限性, 并提出了各种替代方案。 其中之一是 Grad- CAM+++, 根据它的作者, 它可以为网络预测提供更好的视觉解释, 并且可以更好地定位目标, 即使在单个图像中出现多个对象实例时也是如此 。 在这里, 我们显示 Grad- CAM++ 实际上等同于Grad- CAM 的一个非常简单的变异, 以正梯度取代梯度 。