10 citations · 11 across the 3 of their papers we have counts for
3 papers · 1 filter
Distributional Shifts in Automated Diabetic Retinopathy Screening
Jay Nandy, Wynne Hsu, Mong Li Lee
Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening. However, their classification accuracy deg…
Towards Fully Interpretable Deep Neural Networks: Are We There Yet?
Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DN…
Comprehensible Convolutional Neural Networks via Guided Concept Learning
Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the fe…