3 papers
cs.CV2025
ViConEx-Med: Visual Concept Explainability via Multi-Concept Token Transformer for Medical Image Analysis
Cristiano Patrício, Luís F. Teixeira, João C. Neves
Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing…
cs.CV2025
CBVLM: Training-free Explainable Concept-based Large Vision Language Models for Medical Image Classification
Cristiano Patrício, Isabel Rio-Torto, Jaime S. Cardoso +2
The main challenges limiting the adoption of deep learning-based solutions in medical workflows are the availability of annotated data and the lack of interpretability of such syst…
cs.CV2024
A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis
Cristiano Patrício, Luís F. Teixeira, João C. Neves
The main challenges hindering the adoption of deep learning-based systems in clinical settings are the scarcity of annotated data and the lack of interpretability and trust in thes…