Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Donnelly, Jon, Barnett, Alina Jade, Chen, Chaofan
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911863653007360
author Donnelly, Jon
Barnett, Alina Jade
Chen, Chaofan
author_facet Donnelly, Jon
Barnett, Alina Jade
Chen, Chaofan
contents We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by comparing them with prototypes learned during training, yielding explanations in the form of "this looks like that." However, while previous methods use spatially rigid prototypes, we address this shortcoming by proposing spatially flexible prototypes. Each prototype is made up of several prototypical parts that adaptively change their relative spatial positions depending on the input image. Consequently, a Deformable ProtoPNet can explicitly capture pose variations and context, improving both model accuracy and the richness of explanations provided. Compared to other case-based interpretable models using prototypes, our approach achieves state-of-the-art accuracy and gives an explanation with greater context. The code is available at https://github.com/jdonnelly36/Deformable-ProtoPNet.
format Preprint
id arxiv_https___arxiv_org_abs_2111_15000
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes
Donnelly, Jon
Barnett, Alina Jade
Chen, Chaofan
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by comparing them with prototypes learned during training, yielding explanations in the form of "this looks like that." However, while previous methods use spatially rigid prototypes, we address this shortcoming by proposing spatially flexible prototypes. Each prototype is made up of several prototypical parts that adaptively change their relative spatial positions depending on the input image. Consequently, a Deformable ProtoPNet can explicitly capture pose variations and context, improving both model accuracy and the richness of explanations provided. Compared to other case-based interpretable models using prototypes, our approach achieves state-of-the-art accuracy and gives an explanation with greater context. The code is available at https://github.com/jdonnelly36/Deformable-ProtoPNet.
title Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2111.15000