On the stability, correctness and plausibility of visual explanation methods based on feature importance
Not on the map. Why?
Abstract (arXiv)
In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w.r.t. a set of desired properties. In this work, we study the articulation between the stability, correctness and plausibility of explanations based on feature importance for image classifiers. We show that the existing metrics for evaluating these properties do not always agree, raising the issue of what constitutes a good evaluation metric for explanations. Finally, in the particular case of stability and correctness, we show the possible limitations of some evaluation metrics and propose new ones that take into account the local behaviour of the model under test.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 35 references that are in the map. First posted on arXiv 25 Oct 2023.
Builds on
27 of 35 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
- 2018Sanity Checks for Saliency Mapscited by 1,156
- 2017SmoothGrad: removing noise by adding noisecited by 1,109
- 2014Striving for Simplicity: The All Convolutional Netcited by 990
- 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
- 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
15 more
- 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
- 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
- 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
- 2019Sanity Checks for Saliency Metricscited by 119
- 2018Model Agnostic Supervised Local Explanationscited by 83
- 2017Deep Visual Attention Predictioncited by 70
- 2018A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizationscited by 60
- 2022Rethinking Stability for Attribution-based Explanationscited by 52
- 2021Explainable Artificial Intelligence Approaches: A Surveycited by 40
- 2022Metrics for saliency map evaluation of deep learning explanation methodscited by 40
- 2021Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysiscited by 25
- 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
- 2021White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Taskscited by 3
- 2022Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metricscited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.