We present a new technique that explains the output of a CNN-based model using a combination of GradCAM and LRP methods. Both of these methods produce visual explanations by highlighting input regions that are important for predictions. In the new method, the explanation produced by GradCAM is first processed to remove noises. The processed output is then multiplied elementwise with the output of LRP. Finally, a Gaussian blur is applied on the product. We compared the proposed method with GradCAM and LRP on the metrics of Faithfulness, Robustness, Complexity, Localisation and Randomisation. It was observed that this method performs better on Complexity than both GradCAM and LRP and is better than atleast one of them in the other metrics.

翻译：我们提出一种新技术，通过结合GradCAM与LRP方法解释基于CNN模型的输出。这两种方法均通过突出对预测重要的输入区域生成可视化解释。在新方法中，首先对GradCAM生成的解释进行噪声去除处理，然后将处理后的输出与LRP输出逐元素相乘，最后对乘积结果施加高斯模糊处理。我们在忠实度、鲁棒性、复杂度、定位性和随机性指标上将该方法与GradCAM及LRP进行了对比。实验表明，该方法在复杂度指标上优于GradCAM和LRP，且在其余指标上至少优于其中一种方法。