论文标题
使用几何时刻提高深层网络中的形状意识和可解释性
Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
论文作者
论文摘要
与对象形状相比，用于图像分类的深网通常更多地依赖于纹理信息。尽管已经努力使模型具有深度模型，但通常很难使此类模型简单，可解释或植根于已知的数学定义。本文提出了一个受几何矩启发的深度学习模型，这是一种经典的理解方法，可以测量与形状相关的特性。所提出的方法由一个可训练的网络组成，该网络用于生成坐标基碱基和仿射参数，用于使特征不变，但以特定于任务的方式使特征不变。提出的模型改善了最终功能的解释。我们演示了我们方法对标准图像分类数据集的有效性。与基线和标准重新网络模型相比，提出的模型可以实现更高的分类性能，同时实质上提高了可解释性。
Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments, a classically well understood approach to measure shape-related properties. The proposed method consists of a trainable network for generating coordinate bases and affine parameters for making the features geometrically invariant yet in a task-specific manner. The proposed model improves the final feature's interpretation. We demonstrate the effectiveness of our method on standard image classification datasets. The proposed model achieves higher classification performance compared to the baseline and standard ResNet models while substantially improving interpretability.
