# Human-Centered Evaluation of XAI Methods

arXiv: https://arxiv.org/abs/2310.07534 · HTML: https://mlsanity.com/paper/2310.07534/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Human-Centered Explainable AI (XAI): From Algorithms to User Experiences](https://mlsanity.com/paper/2110.10790/) (2021)
- [Towards Explainable Artificial Intelligence](https://mlsanity.com/paper/1909.12072/) (2019)
- [Explainable Artificial Intelligence (XAI) from a user perspective- A synthesis of prior literature and problematizing avenues for future research](https://mlsanity.com/paper/2211.15343/) (2022)
- [Image Features Influence Reaction Time: A Learned Probabilistic Perceptual Model for Saccade Latency](https://mlsanity.com/paper/2205.02437/) (2022)

## Built on by (most cited first, 5 of 5)

- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [False Sense of Security in Explainable Artificial Intelligence (XAI)](https://mlsanity.com/paper/2405.03820/) (2024)
- [This Probably Looks Exactly Like That: An Invertible Prototypical Network](https://mlsanity.com/paper/2407.12200/) (2024)
- [Event-Level Detection of Surgical Instrument Handovers in Videos with Interpretable Vision Models](https://mlsanity.com/paper/2604.07577/) (2026)
- [Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors](https://mlsanity.com/paper/2606.31421/) (2026)

## Abstract (arXiv)

In the ever-evolving field of Artificial Intelligence, a critical challenge has been to decipher the decision-making processes within the so-called "black boxes" in deep learning. Over recent years, a plethora of methods have emerged, dedicated to explaining decisions across diverse tasks. Particularly in tasks like image classification, these methods typically identify and emphasize the pivotal pixels that most influence a classifier's prediction. Interestingly, this approach mirrors human behavior: when asked to explain our rationale for classifying an image, we often point to the most salient features or aspects. Capitalizing on this parallel, our research embarked on a user-centric study. We sought to objectively measure the interpretability of three leading explanation methods: (1) Prototypical Part Network, (2) Occlusion, and (3) Layer-wise Relevance Propagation. Intriguingly, our results highlight that while the regions spotlighted by these methods can vary widely, they all offer humans a nearly equivalent depth of understanding. This enables users to discern and categorize images efficiently, reinforcing the value of these methods in enhancing AI transparency.