1D Gradient-Weighted Class Activation Mapping, Visualizing Decision Process of Convolutional Neural Network-Based Models in Spectroscopy Analysis

可视化 可解释性 卷积神经网络 人工智能 模式识别(心理学) 计算机科学 过程(计算) 特征(语言学) 人工神经网络 化学 哲学 语言学 操作系统
作者
Guo-yang Shi,Hao-ping Wu,Si-Heng Luo,Xinyu Lu,Bin W. Ren,Qian Zhang,Wei‐Qi Lin,Rui-yun Chen,Ping Guo,Huabin Chen,Zhong‐Qun Tian,Guifang Shao,Yang Liu,Guokun Liu
出处
期刊:Analytical Chemistry [American Chemical Society]
卷期号:95 (26): 9959-9966 被引量:79
标识
DOI:10.1021/acs.analchem.3c01101
摘要

Being characterized by the self-adaption and high accuracy, the deep learning-based models have been widely applied in the 1D spectroscopy-related field. However, the "black-box" operation and "end-to-end" working style of the deep learning normally bring the low interpretability, where a reliable visualization is highly demanded. Although there are some well-developed visualization methods, such as Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM), for the 2D image data, they cannot correctly reflect the weights of the model when being applied to the 1D spectral data, where the importance of position information is not considered. Here, aiming at the visualization of Convolutional Neural Network-based models toward the qualitative and quantitative analysis of 1D spectroscopy, we developed a novel visualization algorithm (1D Grad-CAM) to more accurately display the decision-making process of the CNN-based models. Different from the classical Grad-CAM, with the removal of the gradient averaging (GAP) and the ReLU operations, a significantly improved correlation between the gradient and the spectral location and a more comprehensive spectral feature capture were realized for 1D Grad-CAM. Furthermore, the introduction of difference (purity or linearity) and feature contribute in the CNN output in 1D Grad-CAM achieved a reliable evaluation of the qualitative accuracy and quantitative precision of CNN-based models. Facing the qualitative and adulteration quantitative analysis of vegetable oils by the combination of Raman spectroscopy and ResNet, the visualization by 1D Grad-CAM well reflected the origin of the high accuracy and precision brought by ResNet. In general, 1D Grad-CAM provides a clear vision about the judgment criterion of CNN and paves the way for CNN to a broad application in the field of 1D spectroscopy.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
18781913856完成签到,获得积分10
刚刚
svt177188完成签到,获得积分20
刚刚
1秒前
bkagyin的应助被不弃采纳,获得10
1秒前
丘比特的应助被ku采纳,获得10
2秒前
3秒前
傻子完成签到,获得积分10
4秒前
shine完成签到,获得积分10
5秒前
ccmm发布了新的文献求助10
5秒前
学霸业的应助被9979采纳,获得10
5秒前
潦草发布了新的文献求助10
5秒前
dd完成签到,获得积分20
5秒前
上官若男的应助被兔子采纳,获得10
6秒前
米歇尔发布了新的文献求助10
6秒前
搜集达人的应助被是小鱼采纳,获得10
7秒前
SciGPT的应助被taoshiren采纳,获得10
7秒前
科研通AI2S的应助被18781913856采纳,获得10
7秒前
充电宝的应助被田园采纳,获得10
10秒前
娇娇尚发布了新的文献求助10
10秒前
完美世界的应助被花花采纳,获得10
11秒前
12秒前
12秒前
SciGPT的应助被kalani采纳,获得10
12秒前
潦草完成签到,获得积分20
12秒前
13秒前
明亮白山完成签到 ,获得积分10
13秒前
祁安完成签到,获得积分10
14秒前
tian完成签到 ,获得积分10
15秒前
15秒前
小甲鱼发布了新的文献求助10
15秒前
16秒前
又听风雨完成签到,获得积分10
16秒前
16秒前
不弃发布了新的文献求助10
19秒前
napnap发布了新的文献求助10
19秒前
小学生库里完成签到,获得积分10
19秒前
王小美完成签到,获得积分10
19秒前
19秒前
taoshiren发布了新的文献求助10
20秒前
妙妙发布了新的文献求助10
20秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8189382
求助须知:如何正确求助?哪些是违规求助? 9576691
关于积分的说明 21849410
捐赠科研通 7787318
什么是DOI,文献DOI怎么找? 3435538
关于科研通互助平台的介绍 2559748
邀请新用户注册赠送积分活动 2482509