For instance-level explanation, in order to reveal the relations between high-level semantics and detailed spatial information, this paper proposes a novel cognitive approach to neural networks, which named PANE. Under the guidance of PANE, a novel saliency map representation method, named IOM, is proposed for CNN-like models. We make the comparison with eight state-of-the-art saliency map representation methods. The experimental results show that IOM far outperforms baselines. The work of this paper may bring a new perspective to understand deep neural networks.

翻译：例如,为了揭示高层语义学和详细空间信息之间的关系,本文件建议对神经网络采用一种新的认知方法,称为PANE,在PANE的指导下,为类似CNN的模型建议一种新型突出的地图表示法,称为IOM。我们比较了八个最先进的突出地图表示法。实验结果显示,IOM远远超出了基线。本文的工作可以带来一个新的视角来理解深层神经网络。