Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wickstrøm, Kristoffer, Dorszewski, Teresa, Chen, Siyan, Kampffmeyer, Michael, Wetzer, Elisabeth, Jenssen, Robert
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909971224985600
author Wickstrøm, Kristoffer
Dorszewski, Teresa
Chen, Siyan
Kampffmeyer, Michael
Wetzer, Elisabeth
Jenssen, Robert
author_facet Wickstrøm, Kristoffer
Dorszewski, Teresa
Chen, Siyan
Kampffmeyer, Michael
Wetzer, Elisabeth
Jenssen, Robert
contents Current approaches for designing self-explainable models (SEMs) require complicated training procedures and specific architectures which makes them impractical. With the advance of general purpose foundation models based on Vision Transformers (ViTs), this impracticability becomes even more problematic. Therefore, new methods are necessary to provide transparency and reliability to ViT-based foundation models. In this work, we present a new method for turning any well-trained ViT-based model into a SEM without retraining, which we call Keypoint Counting Classifiers (KCCs). Recent works have shown that ViTs can automatically identify matching keypoints between images with high precision, and we build on these results to create an easily interpretable decision process that is inherently visualizable in the input. We perform an extensive evaluation which show that KCCs improve the human-machine communication compared to recent baselines. We believe that KCCs constitute an important step towards making ViT-based foundation models more transparent and reliable.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17891
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training
Wickstrøm, Kristoffer
Dorszewski, Teresa
Chen, Siyan
Kampffmeyer, Michael
Wetzer, Elisabeth
Jenssen, Robert
Computer Vision and Pattern Recognition
Current approaches for designing self-explainable models (SEMs) require complicated training procedures and specific architectures which makes them impractical. With the advance of general purpose foundation models based on Vision Transformers (ViTs), this impracticability becomes even more problematic. Therefore, new methods are necessary to provide transparency and reliability to ViT-based foundation models. In this work, we present a new method for turning any well-trained ViT-based model into a SEM without retraining, which we call Keypoint Counting Classifiers (KCCs). Recent works have shown that ViTs can automatically identify matching keypoints between images with high precision, and we build on these results to create an easily interpretable decision process that is inherently visualizable in the input. We perform an extensive evaluation which show that KCCs improve the human-machine communication compared to recent baselines. We believe that KCCs constitute an important step towards making ViT-based foundation models more transparent and reliable.
title Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.17891