论文标题
Align-peform-subtrats：用于解释对象差异的介入框架
Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences
论文作者
论文摘要
给定两个对象图像，我们如何在基本对象属性方面解释它们的差异？为了解决这个问题，我们提出了Align-efform-subtrats（ADS） - 解释对象差异的介入框架。通过利用图像空间中的语义对齐作为对基本对象属性的反事实干预措施，可以迭代量化并消除对象属性的差异。结果是一组“分解”的错误度量，这些误差度量解释了基本属性方面的对象差异。实际和合成数据的实验说明了框架的功效。
Given two object images, how can we explain their differences in terms of the underlying object properties? To address this question, we propose Align-Deform-Subtract (ADS) -- an interventional framework for explaining object differences. By leveraging semantic alignments in image-space as counterfactual interventions on the underlying object properties, ADS iteratively quantifies and removes differences in object properties. The result is a set of "disentangled" error measures which explain object differences in terms of the underlying properties. Experiments on real and synthetic data illustrate the efficacy of the framework.
