Related papers: EvalAttAI: A Holistic Approach to Evaluating Attri…

The rapid evolution of machine learning (ML) has led to the widespread adoption of complex "black box" models, such as deep neural networks and ensemble methods. These models exhibit exceptional predictive performance, making them…

Deep learning (DL) has revolutionized the field of document image analysis, showcasing superhuman performance across a diverse set of tasks. However, the inherent black-box nature of deep learning models still presents a significant…

The application of computer vision is gradually increasing across various domains. They employ deep learning models with a black-box nature. Without the ability to explain the behavior of neural networks, especially their decision-making…

Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features…

Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction uncertainties. While…

Feature attribution methods attempt to explain neural network predictions by identifying relevant features. However, establishing a cohesive framework for assessing feature attribution remains a challenge. There are several views through…

Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…

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…

Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of…

While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…

We describe an explainable AI saliency map method for use with deep convolutional neural networks (CNN) that is much more efficient than popular fine-resolution gradient methods. It is also quantitatively similar or better in accuracy. Our…

Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models,…

In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However,…

Deep learning has become the de facto standard and dominant paradigm in image analysis tasks, achieving state-of-the-art performance. However, this approach often results in "black-box" models, whose decision-making processes are difficult…

Recent advancements in artificial intelligence (AI) have facilitated its widespread adoption in primary medical services, addressing the demand-supply imbalance in healthcare. Vision Transformers (ViT) have emerged as state-of-the-art…

eXplainable Artificial Intelligence (XAI) is a sub-field of Artificial Intelligence (AI) that is at the forefront of AI research. In XAI, feature attribution methods produce explanations in the form of feature importance. People often use…

While deep learning models have demonstrated remarkable success in numerous domains, their black-box nature remains a significant limitation, especially in critical fields such as medical image analysis and inference. Existing…

In Autonomous Driving (AD) transparency and safety are paramount, as mistakes are costly. However, neural networks used in AD systems are generally considered black boxes. As a countermeasure, we have methods of explainable AI (XAI), such…

Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. In this paper, we propose a novel interpretable approach that combines attribute regularization of the…

Explainable Artificial Intelligence (XAI) is increasingly rec ognized as essential for deploying machine learning systems in safety critical environments. In Automatic Target Recognition (ATR), where models operate on image, video, radar,…