The paper introduces a diagnostic test for class sensitivity in saliency methods, revealing that many popular techniques produce nearly identical explanations regardless of the predicted class. This limitation appears across different architectures and datasets, indicating a structural issue. To address this, the authors propose CASE, a contrastive explanation method that isolates features uniquely discriminative for the predicted class, and demonstrate its improved fidelity and class specificity through experiments.
arXiv:2411. 05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification.
arXiv:2607. 27904v1 Announce Type: new Abstract: Concept-based explanations are a prevalent way to explain the decisions of complex black-box methods through semantically meaningful, human-interpretable concepts.
arXiv:2606. 07180v1 Announce Type: cross Abstract: The growing demand for transparency in automated decision-making has propelled eXplainable Artificial Intelligence (XAI) to the forefront of machine learning research.
arXiv:2608. 12299v1 Announce Type: cross Abstract: Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable artificial intelligence.
arXiv:2605. 28215v2 Announce Type: replace Abstract: In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples.
The paper introduces a straightforward evaluation method for explanation techniques: by converting each explanation into a predictor that sums the feature effects, the authors assess how accurately this predictor reproduces the original model’s predictions on unseen data. This approach applies to any explanation expressible as a function of features and is demonstrated on PDP, ALE, SHAP, and LIME. The authors theoretically show that summing partial dependence curves yields the optimal additive summary when features are independent, but this property fails with dependent features, and empirical results across diverse datasets confirm that the best-performing method depends on feature dependence.
arXiv:2508.08966v2 Announce Type: replace Abstract: The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a gro...
The paper proposes a new evaluation test for explanation methods: if an explanation accurately captures how a model uses its features, one should be able to reconstruct the model’s predictions from it. The authors convert explanations into predictors by summing feature effects and assess how well these predictors reproduce the model on unseen data, without any fitting. They apply this test to partial dependence plots, accumulated local effects, SHAP, and LIME across multiple datasets and model families, showing that the best method depends on feature dependence and that some existing quality metrics can favor flawed explanations.
The paper introduces a classifier‑free method for generating visual counterfactual explanations (VCEs) using Contrastive Analysis (CA). By separating generative factors common to two datasets from those specific to each class, the approach swaps only the salient factors to produce counterfactual images, thereby avoiding reliance on classifier decision boundaries. Leveraging StyleGAN2’s high‑quality synthesis and a feature‑space latent representation, the method supports multiple salient factors per dataset and achieves superior counterfactual quality on three medical imaging datasets.
arXiv:2403. 06013v2 Announce Type: replace Abstract: This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated.
arXiv:2605. 16651v2 Announce Type: replace-cross Abstract: Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight.
arXiv:2608.26083v2 Announce Type: replace-cross Abstract: Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Auditing for shortcuts requires testing many...