Logic Rule Guided Attribution with Dynamic Ablation

Authors

  • Jianqiao An Tianjin University
  • Yuandu Lai Tianjin University Peng Cheng Laboratory
  • Yahong Han Tianjin University

DOI:

https://doi.org/10.1609/aaai.v36i1.19881

Keywords:

Computer Vision (CV)

Abstract

With the increasing demands for understanding the internal behaviors of deep networks, Explainable AI (XAI) has been made remarkable progress in interpreting the model's decision. A family of attribution techniques has been proposed, highlighting whether the input pixels are responsible for the model's prediction. However, the existing attribution methods suffer from the lack of rule guidance and require further human interpretations. In this paper, we construct the 'if-then' logic rules that are sufficiently precise locally. Moreover, a novel rule-guided method, dynamic ablation (DA), is proposed to find a minimal bound sufficient in an input image to justify the network's prediction and aggregate iteratively to reach a complete attribution. Both qualitative and quantitative experiments are conducted to evaluate the proposed DA. We demonstrate the advantages of our method in providing clear and explicit explanations that are also easy for human experts to understand. Besides, through the attribution on a series of trained networks with different architectures, we show that more complex networks require less information to make a specific prediction.

Downloads

Published

2022-06-28

How to Cite

An, J., Lai, Y., & Han, Y. (2022). Logic Rule Guided Attribution with Dynamic Ablation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 77-85. https://doi.org/10.1609/aaai.v36i1.19881

Issue

Section

AAAI Technical Track on Computer Vision I