3 papers
cs.CV2025
Tell me why: Visual foundation models as self-explainable classifiers
Hugues Turbé, Mina Bjelogrlic, Gianmarco Mengaldo +1
Visual foundation models (VFMs) have become increasingly popular due to their state-of-the-art performance. However, interpretability remains crucial for critical applications. In…
cs.CV2024
ProtoS-ViT: Visual foundation models for sparse self-explainable classifications
Hugues Turbé, Mina Bjelogrlic, Gianmarco Mengaldo +1
Prototypical networks aim to build intrinsically explainable models based on the linear summation of concepts. Concepts are coherent entities that we, as humans, can recognize and…
cs.LG2024
Revisiting the robustness of post-hoc interpretability methods
Jiawen Wei, Hugues Turbé, Gianmarco Mengaldo
Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI), as they pinpoint portions of data that a trained deep learning model deemed imp…