Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ayoobi, Hamed, Potyka, Nico, Toni, Francesca
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2311.15438
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915242126082048
author Ayoobi, Hamed
Potyka, Nico
Toni, Francesca
author_facet Ayoobi, Hamed
Potyka, Nico
Toni, Francesca
contents We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e.g., in ProtoPNet. While earlier approaches associate every class with multiple prototypical-parts, ProtoArgNet uses super-prototypes that combine prototypical-parts into a unified class representation. This is done by combining local activations of prototypes in an MLP-like manner, enabling the localization of prototypes and learning (non-linear) spatial relationships among them. By leveraging a form of argumentation, ProtoArgNet is capable of providing both supporting (i.e. `this looks like that') and attacking (i.e. `this differs from that') explanations. We demonstrate on several datasets that ProtoArgNet outperforms state-of-the-art prototypical-part-learning approaches. Moreover, the argumentation component in ProtoArgNet is customisable to the user's cognitive requirements by a process of sparsification, which leads to more compact explanations compared to state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15438
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]
Ayoobi, Hamed
Potyka, Nico
Toni, Francesca
Computer Vision and Pattern Recognition
Artificial Intelligence
We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e.g., in ProtoPNet. While earlier approaches associate every class with multiple prototypical-parts, ProtoArgNet uses super-prototypes that combine prototypical-parts into a unified class representation. This is done by combining local activations of prototypes in an MLP-like manner, enabling the localization of prototypes and learning (non-linear) spatial relationships among them. By leveraging a form of argumentation, ProtoArgNet is capable of providing both supporting (i.e. `this looks like that') and attacking (i.e. `this differs from that') explanations. We demonstrate on several datasets that ProtoArgNet outperforms state-of-the-art prototypical-part-learning approaches. Moreover, the argumentation component in ProtoArgNet is customisable to the user's cognitive requirements by a process of sparsification, which leads to more compact explanations compared to state-of-the-art approaches.
title ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2311.15438