Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning
Deep learning models have revolutionized numerous fields, yet their decision-making
processes often remain opaque, earning them the characterization of “black-box” models …
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
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 …
topics in computer vision and smart city domains. The growing concern for public and …
[HTML][HTML] Opti-CAM: Optimizing saliency maps for interpretability
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 …
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 …
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 …
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
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 …
is critical for patient evaluation and treatment planning. To reduce the labor and expertise …
Explainability-based knowledge distillation
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 …
Based on the knowledge distilled, we categorize KD methods as label-related and structure …
An experimental investigation into the evaluation of explainability methods
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 …
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 …
despite their effectiveness, they are often perceived as black boxes capable of providing …
Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures
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 …
particularly in application domains where labels have to be provided by specialized expert …