List of scientific and research publications developed in the context of iToBoS project.
- Towards the Interpretability of Deep Learning Models for Human Neuroimaging.
- CLEVR-XAI: A benchmark dataset for the ground truth evaluation of neural network explanations.
- Explain and improve: LRP-inference fine-tuning for image captioning models.
- Finding and removing Clever Hans: Using explanation methods to debug and improve deep models.
- Explaining Machine Learning Models for Clinical Gait Analysis.
- PatClarC: Using pattern concept activation vectors for noise-robust model debugging.
- Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations.
- Measurably Stronger Explanation Reliability via Model Canonization.
- Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement.