Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Ziwei, Leake, David, Ye, Xiaomeng, Crandall, David
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911965592420352
author Zhao, Ziwei
Leake, David
Ye, Xiaomeng
Crandall, David
author_facet Zhao, Ziwei
Leake, David
Ye, Xiaomeng
Crandall, David
contents This short paper presents preliminary research on the Case-Enhanced Vision Transformer (CEViT), a similarity measurement method aimed at improving the explainability of similarity assessments for image data. Initial experimental results suggest that integrating CEViT into k-Nearest Neighbor (k-NN) classification yields classification accuracy comparable to state-of-the-art computer vision models, while adding capabilities for illustrating differences between classes. CEViT explanations can be influenced by prior cases, to illustrate aspects of similarity relevant to those cases.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16981
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
Zhao, Ziwei
Leake, David
Ye, Xiaomeng
Crandall, David
Computer Vision and Pattern Recognition
Artificial Intelligence
This short paper presents preliminary research on the Case-Enhanced Vision Transformer (CEViT), a similarity measurement method aimed at improving the explainability of similarity assessments for image data. Initial experimental results suggest that integrating CEViT into k-Nearest Neighbor (k-NN) classification yields classification accuracy comparable to state-of-the-art computer vision models, while adding capabilities for illustrating differences between classes. CEViT explanations can be influenced by prior cases, to illustrate aspects of similarity relevant to those cases.
title Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2407.16981