Hybrid-Gird:遥感图像细粒度分类可解释方法  

Hybrid-Gird:An explainable method for fine-grained classification of remote sensing images

作　　者：朱凯雯 尤亚楠 曹婧宜 孟钢[2] 乔媛媛[1] 杨洁[1] ZHU Kaiwen;YOU Yanan;CAO Jingyi;MENG Gang;QIAO Yuanyuan;YANG Jie(School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876,China;Beijing Institute of Remote Sensing Information,Beijing 100192,China)

机构地区：[1]北京邮电大学人工智能学院,北京100876 [2]北京市遥感信息研究所,北京100192

出　　处：《遥感学报》2024年第7期1722-1734,共13页NATIONAL REMOTE SENSING BULLETIN

基　　金：国家自然科学基金(编号:62101060)。

摘　　要：基于遥感图像的目标细粒度分类深度神经网络已技术日益成熟,网络决策的可解释性研究是当前细粒度分类深度学习算法进一步提高决策可信度的关键问题。为精确表征对模型决策起决定性作用的本质特征,本文基于博弈竞争理论对遥感图像目标细粒度分类任务进行建模,分析了IG、SmoothGrad、Grad-CAM等可解释性方法在遥感图像目标细粒度分类网络上的适用性,提出了一种尺度自适应的目标细粒度分类本质特征可解释性分析方法Hybrid-Grid,使用像素级与局部特征关系融合算法提高对支撑网络决策的目标本质特征的精确描述能力。结果表明:本文提出的Hybrid-Grid对目标细粒度分类网络的解释效果在ADCC量化评估指标上达到78.87,相较Score-CAM有大幅提升;与SmoothGrad、Grad-CAM的解释结果相对比,本文方法在删除及精度损失实验上表现最好,使EFM-Net的Top-1准确率、Top-5准确率、F1得分分别损失了16.92%、1.61%、17.21%,证明Hybrid-Grid准确解释了对细粒度分类网络决策贡献最大的目标本质特征。本文提出的可解释性分析方法能够更精准地揭示当前目标细粒度分类网络的决策特征依据。At present,the deep neural network for targets fine-grained classification based on remote sensing images has been widely applied in military and civilian fields.The“black box”problem of deep learning network models still makes it difficult for people to understand the decision-making basis of the network in fine-grained classification tasks.This not only limits the possibility of deep neural networks optimizing and improving through feedback guidance,but also makes them unable to be fully trusted by humans and applied in important fields such as military and medical fields.Thus,how to carry out explainability research on its internal decision-making mechanism is the key problem for the current fine-grained algorithm to further improve the credibility of decision-making basis.This article summarized the commonly used explainable methods in existing fine-grained classification networks for remote sensing image targets.On this basis,a mathematical model for the problem of target fine-grained classification is established.It also models the fine-grained classification task of remote sensing image targets based on game competition theory,analyzes the applicability of explainable methods such as IG,SmoothGrad,and Grad CAM on the fine-grained classification network of remote sensing image targets,and proposes a scale adaptive method for analyzing the explainability of essential features of fine-grained classification of targets,that is,Hybrid Grid.The fusion algorithm of pixel level and local feature relationships is used to improve the accurate description ability of essential features of targets that support network decision-making.The typical explaining methods involved in this article were evaluated using indicators such as Average Drop,Coherence,Complexity,ADCC,and Deletion and precision loss,confirming the accuracy of the proposed method.The experimental results show that the Hybrid-Grid proposed in this paper achieves a score of 78.87 on the quantitative evaluation index of ADCC for target fine-grained class

关 键 词：遥感图像 可解释性分析方法 目标细粒度分类网络 可解释人工智能 合作博弈理论 本质特征 

分 类 号：TP701[自动化与计算机技术—检测技术与自动化装置] P2[自动化与计算机技术—控制科学与工程]