3 papers
cs.CV2025
Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks
Michail Mamalakis, Antonios Mamalakis, Ingrid Agartz +4
The accelerated progress of artificial intelligence (AI) has popularized deep learning models across various domains, yet their inherent opacity poses challenges, particularly in c…
cs.CV2024
An explainable three dimension framework to uncover learning patterns: A unified look in variable sulci recognition
Michail Mamalakis, Heloise de Vareilles, Atheer AI-Manea +8
The significant features identified in a representative subset of the dataset during the learning process of an artificial intelligence model are referred to as a 'global' explanat…
eess.IV2024
Contrastive-Adversarial and Diffusion: Exploring pre-training and fine-tuning strategies for sulcal identification
Michail Mamalakis, Héloïse de Vareilles, Shun-Chin Jim Wu +7
In the last decade, computer vision has witnessed the establishment of various training and learning approaches. Techniques like adversarial learning, contrastive learning, diffusi…