Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences

03/09/2022
by   Cian Eastwood, et al.
0

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 their underlying properties. Experiments on real and synthetic data illustrate the efficacy of the framework.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset