Adversarial attacks and defenses in explainable artificial intelligence: A survey
H Baniecki, P Biecek - Information Fusion, 2024 - Elsevier
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 …
and trusting statistical and deep learning models, as well as interpreting their predictions …
Toward transparent ai: A survey on interpreting the inner structures of deep neural networks
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 …
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …
Pip-net: Patch-based intuitive prototypes for interpretable image classification
M Nauta, J Schlötterer… - Proceedings of the …, 2023 - openaccess.thecvf.com
Interpretable methods based on prototypical patches recognize various components in an
image in order to explain their reasoning to humans. However, existing prototype-based …
image in order to explain their reasoning to humans. However, existing prototype-based …
Explainable image classification: The journey so far and the road ahead
V Kamakshi, NC Krishnan - AI, 2023 - mdpi.com
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 …
the interpretability challenges posed by complex machine learning models. In this survey …
This looks like those: Illuminating prototypical concepts using multiple visualizations
We present ProtoConcepts, a method for interpretable image classification combining deep
learning and case-based reasoning using prototypical parts. Existing work in prototype …
learning and case-based reasoning using prototypical parts. Existing work in prototype …
Icicle: Interpretable class incremental continual learning
D Rymarczyk, J van de Weijer… - Proceedings of the …, 2023 - openaccess.thecvf.com
Continual learning enables incremental learning of new tasks without forgetting those
previously learned, resulting in positive knowledge transfer that can enhance performance …
previously learned, resulting in positive knowledge transfer that can enhance performance …
Protoseg: Interpretable semantic segmentation with prototypical parts
We introduce ProtoSeg, a novel model for interpretable semantic image segmentation,
which constructs its predictions using similar patches from the training set. To achieve …
which constructs its predictions using similar patches from the training set. To achieve …
Optimized hybrid YOLOu‐Quasi‐ProtoPNet for insulators classification
SF Stefenon, G Singh, BJ Souza… - IET Generation …, 2023 - Wiley Online Library
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 …
grid. Nowadays, several inspections are conducted considering the use of aerial images …
Adversarial counterfactual visual explanations
Counterfactual explanations and adversarial attacks have a related goal: flipping output
labels with minimal perturbations regardless of their characteristics. Yet, adversarial attacks …
labels with minimal perturbations regardless of their characteristics. Yet, adversarial attacks …
Learning support and trivial prototypes for interpretable image classification
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 …
classification by associating predictions with a set of training prototypes, which we refer to as …