Reinforcement Explanation Learning

TL;DR

This paper introduces a reinforcement learning-based method for generating saliency maps as explanations for deep learning classifiers, improving efficiency and accuracy over existing black-box explanation techniques.

Contribution

It formulates saliency map generation as a sequential search problem and leverages reinforcement learning to produce high-quality explanations more efficiently.

Findings

Outperforms state-of-the-art methods in inference time

Maintains explanation quality while reducing computational cost

Validated on three benchmark datasets

Abstract

Deep Learning has become overly complicated and has enjoyed stellar success in solving several classical problems like image classification, object detection, etc. Several methods for explaining these decisions have been proposed. Black-box methods to generate saliency maps are particularly interesting due to the fact that they do not utilize the internals of the model to explain the decision. Most black-box methods perturb the input and observe the changes in the output. We formulate saliency map generation as a sequential search problem and leverage upon Reinforcement Learning (RL) to accumulate evidence from input images that most strongly support decisions made by a classifier. Such a strategy encourages to search intelligently for the perturbations that will lead to high-quality explanations. While successful black box explanation approaches need to rely on heavy computations and suffer from small sample approximation, the deterministic policy learned by our method makes it a lot more efficient during the inference. Experiments on three benchmark datasets demonstrate the superiority of the proposed approach in inference time over state-of-the-arts without hurting the performance. Project Page: https://cvir.github.io/projects/rexl.html