Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

E ŞAHiN, NN Arslan, D Özdemir - Neural Computing and Applications, 2024 - Springer
Deep learning models have revolutionized numerous fields, yet their decision-making
processes often remain opaque, earning them the characterization of “black-box” models …

A review and comparative study of explainable deep learning models applied on action recognition in real time

SA Mahmoudi, O Amel, S Stassin, M Liagre… - Electronics, 2023 - mdpi.com
Video surveillance and image acquisition systems represent one of the most active research
topics in computer vision and smart city domains. The growing concern for public and …

[HTML][HTML] Opti-CAM: Optimizing saliency maps for interpretability

H Zhang, F Torres, R Sicre, Y Avrithis… - Computer Vision and …, 2024 - Elsevier
Methods based on class activation maps (CAM) provide a simple mechanism to interpret
predictions of convolutional neural networks by using linear combinations of feature maps …

Artificial intelligence in endodontics: Data preparation, clinical applications, ethical considerations, limitations, and future directions

H Mohammad‐Rahimi, F Sohrabniya… - International …, 2024 - Wiley Online Library
Artificial intelligence (AI) is emerging as a transformative technology in healthcare, including
endodontics. A gap in knowledge exists in understanding AI's applications and limitations …

Explainable artificial intelligence (XAI): from inherent explainability to large language models

F Mumuni, A Mumuni - arxiv preprint arxiv:2501.09967, 2025 - arxiv.org
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 …

Ame-cam: Attentive multiple-exit cam for weakly supervised segmentation on mri brain tumor

YJ Chen, X Hu, Y Shi, TY Ho - International Conference on Medical Image …, 2023 - Springer
Magnetic resonance imaging (MRI) is commonly used for brain tumor segmentation, which
is critical for patient evaluation and treatment planning. To reduce the labor and expertise …

Explainability-based knowledge distillation

T Sun, H Chen, G Hu, C Zhao - Pattern Recognition, 2025 - Elsevier
Abstract Knowledge distillation (KD) is a popular approach for deep model acceleration.
Based on the knowledge distilled, we categorize KD methods as label-related and structure …

An experimental investigation into the evaluation of explainability methods

S Stassin, A Englebert, G Nanfack, J Albert… - arxiv preprint arxiv …, 2023 - arxiv.org
EXplainable Artificial Intelligence (XAI) aims to help users to grasp the reasoning behind the
predictions of an Artificial Intelligence (AI) system. Many XAI approaches have emerged in …

From CNN to ConvRNN: Adapting Visualization Techniques for Time-Series Anomaly Detection

F Poirier - arxiv preprint arxiv:2411.04707, 2024 - arxiv.org
Nowadays, neural networks are commonly used to solve various problems. Unfortunately,
despite their effectiveness, they are often perceived as black boxes capable of providing …

Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures

K Janouskova, M Rigotti, I Giurgiu… - European Conference on …, 2022 - Springer
Labeling images for visual segmentation is a time-consuming task which can be costly,
particularly in application domains where labels have to be provided by specialized expert …