The surge in black-box AI models has prompted the need to explain the internal mechanism
and justify their reliability, especially in high-stakes applications, such as healthcare and …

As deep learning (DL) efficacy grows, concerns for poor model explainability grow also.
Attribution methods address the issue of explainability by quantifying the importance of an …

Abstract We introduce Iterated Integrated Attributions (IIA)-a generic method for explaining
the predictions of vision models. IIA employs iterative integration across the input image, the …

Purpose Artificial intelligence (AI), in particular deep neural networks, has achieved
remarkable results for medical image analysis in several applications. Yet the lack of …

Integrated Gradients (IG) as well as its variants are well-known techniques for interpreting
the decisions of deep neural networks. While IG-based approaches attain state-of-the-art …

In this paper we explore the unique modality of sketch for explainability emphasising the
profound impact of human strokes compared to conventional pixel-oriented studies. Beyond …

The most promising standard machine learning methods can deliver highly accurate
classification results, often outperforming standard white-box methods. However, it is hardly …

Artificial Intelligence (AI) has continued to achieve tremendous success in recent times.
However, the decision logic of these frameworks is often not transparent, making it difficult …

Interpreting the decisions of deep learning models has been actively studied since the
explosion of deep neural networks. One of the most convincing interpretation approaches is …

Deep learning models have been increasingly applied to medical images for tasks such as
lesion detection, segmentation, and diagnosis. However, the field suffers from the lack of …