Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging
and trusting statistical and deep learning models, as well as interpreting their predictions …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

Interpretable methods based on prototypical patches recognize various components in an
image in order to explain their reasoning to humans. However, existing prototype-based …

Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address
the interpretability challenges posed by complex machine learning models. In this survey …

We present ProtoConcepts, a method for interpretable image classification combining deep
learning and case-based reasoning using prototypical parts. Existing work in prototype …

Continual learning enables incremental learning of new tasks without forgetting those
previously learned, resulting in positive knowledge transfer that can enhance performance …

We introduce ProtoSeg, a novel model for interpretable semantic image segmentation,
which constructs its predictions using similar patches from the training set. To achieve …

To ensure the electrical power supply, inspections are frequently performed in the power
grid. Nowadays, several inspections are conducted considering the use of aerial images …

Counterfactual explanations and adversarial attacks have a related goal: flipping output
labels with minimal perturbations regardless of their characteristics. Yet, adversarial attacks …

Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable
classification by associating predictions with a set of training prototypes, which we refer to as …