Accurate Explanation Model for Image Classifiers using Class Association Embedding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xie, Ruitao, Chen, Jingbang, Jiang, Limai, Xiao, Rui, Pan, Yi, Cai, Yunpeng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915082775035904
author Xie, Ruitao
Chen, Jingbang
Jiang, Limai
Xiao, Rui
Pan, Yi
Cai, Yunpeng
author_facet Xie, Ruitao
Chen, Jingbang
Jiang, Limai
Xiao, Rui
Pan, Yi
Cai, Yunpeng
contents Image classification is a primary task in data analysis where explainable models are crucially demanded in various applications. Although amounts of methods have been proposed to obtain explainable knowledge from the black-box classifiers, these approaches lack the efficiency of extracting global knowledge regarding the classification task, thus is vulnerable to local traps and often leads to poor accuracy. In this study, we propose a generative explanation model that combines the advantages of global and local knowledge for explaining image classifiers. We develop a representation learning method called class association embedding (CAE), which encodes each sample into a pair of separated class-associated and individual codes. Recombining the individual code of a given sample with altered class-associated code leads to a synthetic real-looking sample with preserved individual characters but modified class-associated features and possibly flipped class assignments. A building-block coherency feature extraction algorithm is proposed that efficiently separates class-associated features from individual ones. The extracted feature space forms a low-dimensional manifold that visualizes the classification decision patterns. Explanation on each individual sample can be then achieved in a counter-factual generation manner which continuously modifies the sample in one direction, by shifting its class-associated code along a guided path, until its classification outcome is changed. We compare our method with state-of-the-art ones on explaining image classification tasks in the form of saliency maps, demonstrating that our method achieves higher accuracies. The code is available at https://github.com/xrt11/XAI-CODE.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07961
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accurate Explanation Model for Image Classifiers using Class Association Embedding
Xie, Ruitao
Chen, Jingbang
Jiang, Limai
Xiao, Rui
Pan, Yi
Cai, Yunpeng
Computer Vision and Pattern Recognition
Artificial Intelligence
Image classification is a primary task in data analysis where explainable models are crucially demanded in various applications. Although amounts of methods have been proposed to obtain explainable knowledge from the black-box classifiers, these approaches lack the efficiency of extracting global knowledge regarding the classification task, thus is vulnerable to local traps and often leads to poor accuracy. In this study, we propose a generative explanation model that combines the advantages of global and local knowledge for explaining image classifiers. We develop a representation learning method called class association embedding (CAE), which encodes each sample into a pair of separated class-associated and individual codes. Recombining the individual code of a given sample with altered class-associated code leads to a synthetic real-looking sample with preserved individual characters but modified class-associated features and possibly flipped class assignments. A building-block coherency feature extraction algorithm is proposed that efficiently separates class-associated features from individual ones. The extracted feature space forms a low-dimensional manifold that visualizes the classification decision patterns. Explanation on each individual sample can be then achieved in a counter-factual generation manner which continuously modifies the sample in one direction, by shifting its class-associated code along a guided path, until its classification outcome is changed. We compare our method with state-of-the-art ones on explaining image classification tasks in the form of saliency maps, demonstrating that our method achieves higher accuracies. The code is available at https://github.com/xrt11/XAI-CODE.
title Accurate Explanation Model for Image Classifiers using Class Association Embedding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.07961