# Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics

arXiv: https://arxiv.org/abs/2212.01222 · HTML: https://mlsanity.com/paper/2212.01222/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 2 Dec 2022.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Revisiting Video Saliency: A Large-scale Benchmark and a New Model](https://mlsanity.com/paper/1801.07424/) (2018)
- [Metrics for saliency map evaluation of deep learning explanation methods](https://mlsanity.com/paper/2201.13291/) (2022)
- [Actions in the Eye: Dynamic Gaze Datasets and Learnt Saliency Models for Visual Recognition](https://mlsanity.com/paper/1312.7570/) (2013)
- [CNNPruner: Pruning Convolutional Neural Networks with Visual Analytics](https://mlsanity.com/paper/2009.09940/) (2020)
- [PARTICUL: Part Identification with Confidence measure using Unsupervised Learning](https://mlsanity.com/paper/2206.13304/) (2022)

## Built on by (most cited first, 2 of 2)

- [On the stability, correctness and plausibility of visual explanation methods based on feature importance](https://mlsanity.com/paper/2311.12860/) (2023)
- [Mean Opinion Score as a New Metric for User-Evaluation of XAI Methods](https://mlsanity.com/paper/2407.20427/) (2024)

## Abstract (arXiv)

The most popular methods in AI-machine learning paradigm are mainly black boxes. This is why explanation of AI decisions is of emergency. Although dedicated explanation tools have been massively developed, the evaluation of their quality remains an open research question. In this paper, we generalize the methodologies of evaluation of post-hoc explainers of CNNs' decisions in visual classification tasks with reference and no-reference based metrics. We apply them on our previously developed explainers (FEM, MLFEM), and popular Grad-CAM. The reference-based metrics are Pearson correlation coefficient and Similarity computed between the explanation map and its ground truth represented by a Gaze Fixation Density Map obtained with a psycho-visual experiment. As a no-reference metric, we use stability metric, proposed by Alvarez-Melis and Jaakkola. We study its behaviour, consensus with reference-based metrics and show that in case of several kinds of degradation on input images, this metric is in agreement with reference-based ones. Therefore, it can be used for evaluation of the quality of explainers when the ground truth is not available.