论文标题
用于生成用户定义的3D形状的概念激活向量
Concept Activation Vectors for Generating User-Defined 3D Shapes
论文作者
论文摘要
我们在计算机辅助设计（CAD）的背景下探讨了3D几何深度学习模型的解释性。参数CAD领域可以受到一些数字参数表达高级设计概念的困难。在本文中，我们使用深度学习体系结构将高维3D形状编码为可用于描述任意概念的矢量潜伏表示。具体来说，我们训练一个简单的自动编码器来参数化复杂形状的数据集。为了了解潜在的编码空间，我们使用概念激活向量（CAV）的概念来重新解释潜在空间，以用户定义的概念。这允许修改参考设计，以表现出所选概念或一组概念的更多或更少的特征。我们还测试了已确定的概念的统计意义，并确定了整个数据集的物理量的敏感性。
We explore the interpretability of 3D geometric deep learning models in the context of Computer-Aided Design (CAD). The field of parametric CAD can be limited by the difficulty of expressing high-level design concepts in terms of a few numeric parameters. In this paper, we use a deep learning architectures to encode high dimensional 3D shapes into a vectorized latent representation that can be used to describe arbitrary concepts. Specifically, we train a simple auto-encoder to parameterize a dataset of complex shapes. To understand the latent encoded space, we use the idea of Concept Activation Vectors (CAV) to reinterpret the latent space in terms of user-defined concepts. This allows modification of a reference design to exhibit more or fewer characteristics of a chosen concept or group of concepts. We also test the statistical significance of the identified concepts and determine the sensitivity of a physical quantity of interest across the dataset.
