P-TAME: Explain Any Image Classifier With Trained Perturbations

IF 2.9 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Mariano V. Ntrougkas;Vasileios Mezaris;Ioannis Patras
{"title":"P-TAME: Explain Any Image Classifier With Trained Perturbations","authors":"Mariano V. Ntrougkas;Vasileios Mezaris;Ioannis Patras","doi":"10.1109/OJSP.2025.3568756","DOIUrl":null,"url":null,"abstract":"The adoption of Deep Neural Networks (DNNs) in critical fields where predictions need to be accompanied by justifications is hindered by their inherent black-box nature. This paper introduces P-TAME (Perturbation-based Trainable Attention Mechanism for Explanations), a model-agnostic method for explaining DNN-based image classifiers. P-TAME employs an auxiliary image classifier to extract features from the input image, bypassing the need to tailor the explanation method to the internal architecture of the backbone classifier being explained. Unlike traditional perturbation-based methods, which have high computational requirements, P-TAME offers an efficient alternative by generating high-resolution explanations in a single forward pass during inference. We apply P-TAME to explain the decisions of VGG-16, ResNet-50, and ViT-B-16, three distinct and widely used image classifiers. Quantitative and qualitative results show that P-TAME matches or outperforms previous explainability methods, including model-specific ones.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"536-545"},"PeriodicalIF":2.9000,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10994422","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE open journal of signal processing","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10994422/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

The adoption of Deep Neural Networks (DNNs) in critical fields where predictions need to be accompanied by justifications is hindered by their inherent black-box nature. This paper introduces P-TAME (Perturbation-based Trainable Attention Mechanism for Explanations), a model-agnostic method for explaining DNN-based image classifiers. P-TAME employs an auxiliary image classifier to extract features from the input image, bypassing the need to tailor the explanation method to the internal architecture of the backbone classifier being explained. Unlike traditional perturbation-based methods, which have high computational requirements, P-TAME offers an efficient alternative by generating high-resolution explanations in a single forward pass during inference. We apply P-TAME to explain the decisions of VGG-16, ResNet-50, and ViT-B-16, three distinct and widely used image classifiers. Quantitative and qualitative results show that P-TAME matches or outperforms previous explainability methods, including model-specific ones.
解释任何带有训练扰动的图像分类器
深度神经网络(dnn)在预测需要证明的关键领域的采用受到其固有黑箱性质的阻碍。本文介绍了基于微扰的可训练注意解释机制(P-TAME),这是一种用于解释基于dnn的图像分类器的模型不可知方法。P-TAME使用一个辅助图像分类器从输入图像中提取特征,而不需要根据被解释的主分类器的内部架构定制解释方法。与传统的基于微扰的方法不同,P-TAME提供了一种高效的替代方案,通过在推理过程中的单个前向传递中生成高分辨率的解释。我们应用P-TAME来解释VGG-16、ResNet-50和vitb -16这三种不同且广泛使用的图像分类器的决策。定量和定性结果表明,P-TAME匹配或优于以前的可解释性方法,包括特定于模型的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.30
自引率
0.00%
发文量
0
审稿时长
22 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信