Reinforcement Explanation Learning

by   Siddhant Agarwal, et al.

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:


page 8

page 16

page 17

page 19

page 20

page 22

page 24

page 25


Black Box Explanation by Learning Image Exemplars in the Latent Feature Space

We present an approach to explain the decisions of black box models for ...

iGOS++: Integrated Gradient Optimized Saliency by Bilateral Perturbations

The black-box nature of the deep networks makes the explanation for "why...

Model-agnostic explainable artificial intelligence for object detection in image data

Object detection is a fundamental task in computer vision, which has bee...

McXai: Local model-agnostic explanation as two games

To this day, a variety of approaches for providing local interpretabilit...

Ablation Path Saliency

Various types of saliency methods have been proposed for explaining blac...

A Rate-Distortion Framework for Explaining Black-box Model Decisions

We present the Rate-Distortion Explanation (RDE) framework, a mathematic...

Explanation by Progressive Exaggeration

As machine learning methods see greater adoption and implementation in h...

Please sign up or login with your details

Forgot password? Click here to reset