4 papers
Hybrid Interpretable Deep Learning Framework for Skin Cancer Diagnosis: Integrating Radial Basis Function Networks with Explainable AI
Mirza Ahsan Ullah, Tehseen Zia
Skin cancer is one of the most prevalent and potentially life-threatening diseases worldwide, necessitating early and accurate diagnosis to improve patient outcomes. Conventional d…
Leveraging counterfactual concepts for debugging and improving CNN model performance
Syed Ali Tariq, Tehseen Zia
Counterfactual explanation methods have recently received significant attention for explaining CNN-based image classifiers due to their ability to provide easily understandable exp…
Faithful Counterfactual Visual Explanations (FCVE)
Bismillah Khan, Syed Ali Tariq, Tehseen Zia +2
Deep learning models in computer vision have made remarkable progress, but their lack of transparency and interpretability remains a challenge. The development of explainable AI ca…
Towards Counterfactual and Contrastive Explainability and Transparency of DCNN Image Classifiers
Syed Ali Tariq, Tehseen Zia, Mubeen Ghafoor
Explainability of deep convolutional neural networks (DCNNs) is an important research topic that tries to uncover the reasons behind a DCNN model's decisions and improve their unde…