Explainable Features in Classification of Neonatal Thermograms

Örnek, Ahmet Haydar; Ceylan, Murat

doi:10.1109/siu49456.2020.9302311

Cited by 1 publication

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Visual methods are another approach to explaining deep Convolutional Neural Networks (CNNs), by identifying the most essential parts of the content. One standard method is to visualize the convolution filters and layers to understand whether the model is learning effectively [26]. If the layers reveal unrelated parts to the desired classes, it may indicate overfitting or other issues that require further exploration.…”

Section: Related Workmentioning

confidence: 99%

Improving Explainability in CNN-Based Classification of Mask Images with HayCAM+: An Enhanced Visual Explanation Technique

Ornek,

Ceylan

2024

View full text Add to dashboard Cite

Deep learning models are proficient at predicting target classes, but they need to explain their predictions. Explainable Artificial Intelligence (XAI) offers a promising solution by providing both transparency and object detection capabilities to classification models. Mask detection plays a crucial role in ensuring the safety and well-being of individuals by preventing the spread of infectious diseases. A new visual XAI method called HayCAM+ is proposed to address the limitations of the previous method known as HayCAM, such as the need to select the number of filters as a hyper-parameter and the use of fully-connected layers. When object detection is performed using activation maps created via various methods, including GradCAM, EigenCAM, GradCAM++, LayerCAM, HayCAM, and HayCAM+, it is found that HayCAM+ provides the best results with an IoU score of 0.3740

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Explainability in CNN-Based Classification of Mask Images with HayCAM+: An Enhanced Visual Explanation Technique

Ornek,

Ceylan

2024

View full text Add to dashboard Cite

show abstract

Explainable Features in Classification of Neonatal Thermograms

Cited by 1 publication

References 15 publications

Improving Explainability in CNN-Based Classification of Mask Images with HayCAM+: An Enhanced Visual Explanation Technique

Improving Explainability in CNN-Based Classification of Mask Images with HayCAM+: An Enhanced Visual Explanation Technique

Contact Info

Product

Resources

About