Existing prototypical-based models address the black-box nature of deep learning.
However, they are sub-optimal as they often assume separate prototypes for each class …

Existing prototypical-based models address the black-box nature of deep learning.
However, they are sub-optimal as they often assume separate prototypes for each class …

We introduce ProtoPool, an interpretable image classification model with a pool of
prototypes shared by the classes. The training is more straightforward than in the existing …

Existing prototypical-based models address the black-box nature of deep learning.
However, they are sub-optimal as they often assume separate prototypes for each class …

We introduce ProtoPool, an interpretable image classification model with a pool of
prototypes shared by the classes. The training is more straightforward than in the existing …

Existing prototypical-based models address the black-box nature of deep learning.
However, they are sub-optimal as they often assume separate prototypes for each class …

Interpretable image classification with differentiable prototypes assignment Przejdź do treści
Pomoc A A A Zmień kontrast Zaloguj English polski   Repozytorium Uniwersytetu …