论文标题
VS-CAM：顶点语义类激活映射以解释视觉图形神经网络
VS-CAM: Vertex Semantic Class Activation Mapping to Interpret Vision Graph Neural Network
论文作者
论文摘要
图形卷积神经网络（GCN）吸引了越来越多的注意力，并在各种计算机视觉任务中取得了良好的表现，但是，对GCN的内部机制缺乏明确的解释。对于标准的卷积神经网络（CNN），通常使用类激活映射（CAM）方法通过生成热图来可视化CNN的决策和图像区域之间的连接。尽管如此，当这些凸轮直接应用于GCN时，这种热图通常会显示出语义 - chaos。在本文中，我们提出了一种新型的可视化方法，特别适用于GCN，顶点语义类激活映射（VS-CAM）。 VS-CAM包括两个独立的管道，分别产生一组语义探针图和一个语义基映射。语义探针图用于检测语义信息从语义碱图图中进行汇总的语义吸引热图。定性结果表明，VS-CAM可以获得与基于CNN的CAM更精确地匹配对象的热图。定量评估进一步证明了VS-CAM的优势。
Graph convolutional neural network (GCN) has drawn increasing attention and attained good performance in various computer vision tasks, however, there lacks a clear interpretation of GCN's inner mechanism. For standard convolutional neural networks (CNNs), class activation mapping (CAM) methods are commonly used to visualize the connection between CNN's decision and image region by generating a heatmap. Nonetheless, such heatmap usually exhibits semantic-chaos when these CAMs are applied to GCN directly. In this paper, we proposed a novel visualization method particularly applicable to GCN, Vertex Semantic Class Activation Mapping (VS-CAM). VS-CAM includes two independent pipelines to produce a set of semantic-probe maps and a semantic-base map, respectively. Semantic-probe maps are used to detect the semantic information from semantic-base map to aggregate a semantic-aware heatmap. Qualitative results show that VS-CAM can obtain heatmaps where the highlighted regions match the objects much more precisely than CNN-based CAM. The quantitative evaluation further demonstrates the superiority of VS-CAM.
