{"slug": "few-class-fidelity-evaluating-explanations-of-real-conditions-cnn-classifiers", "title": "Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations", "summary": "Researchers propose a variation of Fidelity-based XAI metrics for evaluating explanations of CNN classifiers in real-world applications with few classes. The method generates in-distribution, uncertainty-provoking perturbations to measure faithfulness, and tests on medical and natural imaging reveal correlations between domain, data curation, and XAI choices.", "body_md": "arXiv:2606.28391v1 Announce Type: new\nAbstract: The wide use of Convolutional Neural Networks (CNN) in numerous domains and real-world classification applications is justified by their high precision and automation speed, helping users concentrate on higher-expertise tasks. To better understand the models and avoid bias during deployment, eXplainable Artificial Intelligence (XAI) techniques can be used after training. But as the list of XAI solutions expand, comparisons between them diverge, and consensus over their evaluation cannot be reached. This paper proposes a variation of Fidelity-based XAI metrics, with a focus on real-conditions applications, where the number of classes is often low. The approach generates in-distribution, uncertainty-provoking perturbations, to ensure proper measurement of the XAI methods faithfulness. As demonstration of the evaluation framework usefulness, it is compared with human-centric object localization and segmentation metrics. Once applied to both medical and natural imaging applications, it highlights the intricate correlation between domain, data curation, and XAI solution choices in order to validate training of a new CNN model.", "url": "https://wpnews.pro/news/few-class-fidelity-evaluating-explanations-of-real-conditions-cnn-classifiers", "canonical_source": "https://arxiv.org/abs/2606.28391", "published_at": "2026-06-30 04:00:00+00:00", "updated_at": "2026-06-30 04:24:38.540698+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision", "ai-ethics", "ai-research"], "entities": ["Convolutional Neural Networks", "eXplainable Artificial Intelligence", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/few-class-fidelity-evaluating-explanations-of-real-conditions-cnn-classifiers", "markdown": "https://wpnews.pro/news/few-class-fidelity-evaluating-explanations-of-real-conditions-cnn-classifiers.md", "text": "https://wpnews.pro/news/few-class-fidelity-evaluating-explanations-of-real-conditions-cnn-classifiers.txt", "jsonld": "https://wpnews.pro/news/few-class-fidelity-evaluating-explanations-of-real-conditions-cnn-classifiers.jsonld"}}