# A Unified Framework for Evaluating and Enhancing the Transparency of Explainable AI Methods via Perturbation-Gradient Consensus Attribution

arXiv: https://arxiv.org/abs/2412.03884 · HTML: https://mlsanity.com/paper/2412.03884/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["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)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Using Deep Learning for Image-Based Plant Disease Detection](https://mlsanity.com/paper/1604.03169/) (2016)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)

## Built on by (most cited first, 1 of 1)

- [Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets](https://mlsanity.com/paper/2509.05892/) (2025)

## Abstract (arXiv)

Explainable Artificial Intelligence (XAI) methods are increasingly used in safety-critical domains, yet there is no unified framework to jointly evaluate fidelity, interpretability, robustness, fairness, and completeness. We address this gap through two contributions. First, we propose a multi-criteria evaluation framework that formalizes these five criteria using principled metrics: fidelity via prediction-gap analysis; interpretability via a composite concentration-coherence-contrast score; robustness via cosine-similarity perturbation stability; fairness via Jensen-Shannon divergence across demographic groups; and completeness via feature-ablation coverage. These are integrated using an entropy-weighted dynamic scoring scheme that adapts to domain-specific priorities. Second, we introduce Perturbation-Gradient Consensus Attribution (PGCA), which fuses grid-based perturbation importance with Grad-CAM++ through consensus amplification and adaptive contrast enhancement, combining perturbation fidelity with gradient-based spatial precision. We evaluate across five domains (brain tumor MRI, plant disease, security screening, gender, and sunglass detection) using fine-tuned ResNet-50 models. PGCA achieves the best performance in fidelity (2.22 ± 1.62), interpretability (3.89 ± 0.33), and fairness (4.95 ± 0.03), with statistically significant improvements over baselines (p < 10-7). Sensitivity analysis shows stable rankings (Kendall's (τ ≥ 0.88)). Code and results are publicly available.