# Explainers in the Wild: Making Surrogate Explainers Robust to Distortions through Perception

arXiv: https://arxiv.org/abs/2102.10951 · HTML: https://mlsanity.com/paper/2102.10951/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 11 of 11)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency](https://mlsanity.com/paper/2001.09734/) (2020)
- [bLIMEy: Surrogate Prediction Explanations Beyond LIME](https://mlsanity.com/paper/1910.13016/) (2019)
- [Perceptually Optimized Image Rendering](https://mlsanity.com/paper/1701.06641/) (2017)
- [PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance](https://mlsanity.com/paper/1910.12548/) (2019)
- [Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance](https://mlsanity.com/paper/1908.04347/) (2019)

## Built on by (most cited first, 4 of 4)

- [EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations](https://mlsanity.com/paper/2402.00491/) (2024)
- [Understanding surrogate explanations: the interplay between complexity, fidelity and coverage](https://mlsanity.com/paper/2107.04309/) (2021)
- [Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach](https://mlsanity.com/paper/2111.09121/) (2021)
- [Sampling Based On Natural Image Statistics Improves Local Surrogate Explainers](https://mlsanity.com/paper/2208.03961/) (2022)

## Abstract (arXiv)

Explaining the decisions of models is becoming pervasive in the image processing domain, whether it is by using post-hoc methods or by creating inherently interpretable models. While the widespread use of surrogate explainers is a welcome addition to inspect and understand black-box models, assessing the robustness and reliability of the explanations is key for their success. Additionally, whilst existing work in the explainability field proposes various strategies to address this problem, the challenges of working with data in the wild is often overlooked. For instance, in image classification, distortions to images can not only affect the predictions assigned by the model, but also the explanation. Given a clean and a distorted version of an image, even if the prediction probabilities are similar, the explanation may still be different. In this paper we propose a methodology to evaluate the effect of distortions in explanations by embedding perceptual distances that tailor the neighbourhoods used to training surrogate explainers. We also show that by operating in this way, we can make the explanations more robust to distortions. We generate explanations for images in the Imagenet-C dataset and demonstrate how using a perceptual distances in the surrogate explainer creates more coherent explanations for the distorted and reference images.