Related papers: Systematic Evaluation of Attribution Methods: Elim…

The field of Explainable Artificial Intelligence (XAI) aims to build explainable and interpretable machine learning (or deep learning) methods without sacrificing prediction performance. Convolutional Neural Networks (CNNs) have been…

While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training.…

Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the final output. However, existing attribution methods are often…

Knowledge of the noise distribution in diffusion MRI is the centerpiece to quantify uncertainties arising from the acquisition process. Accurate estimation beyond textbook distributions often requires information about the acquisition…

The integration of medical imaging and clinical text has enabled the emergence of generalist artificial intelligence (AI) systems for healthcare. However, pervasive biases, such as imbalanced disease prevalence, skewed anatomical region…

Background and objective: Prior probability shift between training and deployment datasets challenges deep learning-based medical image classification. Standard correction methods reweight posterior probabilities to adjust prior bias, yet…

The chorioallantoic membrane (CAM) model is a widely used in vivo platform for studying angiogenesis, especially in relation to tumor growth, drug delivery, and vascular biology.Since the topology and morphology of developing blood vessels…

Despite the excelling performance of machine learning models, understanding their decisions remains a long-standing goal. Although commonly used attribution methods from explainable AI attempt to address this issue, they typically rely on…

Bias discovery is critical for black-box generative models, especiall text-to-image (TTI) models. Existing works predominantly focus on output-level demographic distributions, which do not necessarily guarantee concept representations to be…

Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications. Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these…

Shifts in data distribution can substantially harm the performance of clinical AI models and lead to misdiagnosis. Hence, various methods have been developed to detect the presence of such shifts at deployment time. However, the root causes…

The objective of topic inference in research proposals aims to obtain the most suitable disciplinary division from the discipline system defined by a funding agency. The agency will subsequently find appropriate peer review experts from…

Ensuring the trustworthiness and interpretability of machine learning models is critical to their deployment in real-world applications. Feature attribution methods have gained significant attention, which provide local explanations of…

Predictive uncertainties in classification tasks are often a consequence of model inadequacy or insufficient training data. In popular applications, such as image processing, we are often required to scrutinise these uncertainties by…

In the field of eXplainable AI (XAI), robust "blackbox" algorithms such as Convolutional Neural Networks (CNNs) are known for making high prediction performance. However, the ability to explain and interpret these algorithms still require…

As Large Language Models (LLMs) are increasingly applied to document-based tasks - such as document summarization, question answering, and information extraction - where user requirements focus on retrieving information from provided…

In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Recent research addresses…

The lack of transparency of data-driven Artificial Intelligence techniques limits their interpretability and acceptance into healthcare decision-making processes. We propose an attribution-based approach to improve the interpretability of…

We introduce a novel algorithm for estimating optimal parameters of linearized assignment flows for image labeling. An exact formula is derived for the parameter gradient of any loss function that is constrained by the linear system of ODEs…

A vastly growing literature on explaining deep learning models has emerged. This paper contributes to that literature by introducing a global gradient-based model-agnostic method, which we call Marginal Attribution by Conditioning on…