Reinforcement Explanation Learning
arXiv:2111.13406
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
arXiv commentAccepted in NeurIPS 2021 workshop on eXplainable AI approaches for debugging and diagnosis. Project Page: https://cvir.github.io/projects/rexl.html
References in corpus (10)
- Playing Atari with Deep Reinforcement Learning
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Language Models are Few-Shot Learners
- Trust Region Policy Optimization
- How to Explain Individual Classification Decisions
- RISE: Randomized Input Sampling for Explanation of Black-box Models
- Safe and Efficient Off-Policy Reinforcement Learning
- To Explain or Not to Explain: A Study on the Necessity of Explanations for Autonomous Vehicles
- Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
- NormGrad: Finding the Pixels that Matter for Training