Evaluating saliency methods on artificial data with different background types

2021/12/09 by Céline Budding, Fabian Eitel, Budding, Céline +5
Computer Science · Medicine · #Artificial Intelligence in Healthcare and Education #Computer Vision and Pattern Recognition (cs.CV) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2112.04882

openalex publication_date 2021/12/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Over the last years, many 'explainable artificial intelligence' (xAI) approaches have been developed, but these have not always been objectively evaluated. To evaluate the quality of heatmaps generated by various saliency methods, we developed a framework to generate artificial data with synthetic lesions and a known ground truth map. Using this framework, we evaluated two data sets with different backgrounds, Perlin noise and 2D brain MRI slices, and found that the heatmaps vary strongly between saliency methods and backgrounds. We strongly encourage further evaluation of saliency maps and xAI methods using this framework before applying these in clinical or other safety-critical settings.

Related

• Quantifying Explainability of Saliency Methods in Deep Neural Networks with a Synthetic Dataset
• Evaluation of Saliency-based Explainability Method
• Global Saliency: Aggregating Saliency Maps to Assess Dataset Artefact Bias
• Assessing the (Un)Trustworthiness of Saliency Maps for Localizing\n Abnormalities in Medical Imaging
• Assessing the validity of saliency maps for abnormality localization in medical imaging