已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Representation of Imprecision in Deep Neural Networks for Image Classification

人工智能 模式识别(心理学) 人工神经网络 集合(抽象数据类型) 计算机科学 图像(数学) 透视图(图形) 代表(政治) 特征(语言学) 机器学习 深信不疑网络 深度学习 上下文图像分类 过程(计算) 语言学 哲学 政治 政治学 法学 程序设计语言 操作系统
作者
Zuowei Zhang,Zhunga Liu,Liangbo Ning,Arnaud Martin,Jiexuan Xiong
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:: 1-14 被引量:6
标识
DOI:10.1109/tnnls.2023.3329712
摘要

Quantification and reduction of uncertainty in deep-learning techniques have received much attention but ignored how to characterize the imprecision caused by such uncertainty. In some tasks, we prefer to obtain an imprecise result rather than being willing or unable to bear the cost of an error. For this purpose, we investigate the representation of imprecision in deep-learning (RIDL) techniques based on the theory of belief functions (TBF). First, the labels of some training images are reconstructed using the learning mechanism of neural networks to characterize the imprecision in the training set. In the process, a label assignment rule is proposed to reassign one or more labels to each training image. Once an image is assigned with multiple labels, it indicates that the image may be in an overlapping region of different categories from the feature perspective or the original label is wrong. Second, those images with multiple labels are rechecked. As a result, the imprecision (multiple labels) caused by the original labeling errors will be corrected, while the imprecision caused by insufficient knowledge is retained. Images with multiple labels are called imprecise ones, and they are considered to belong to meta-categories, the union of some specific categories. Third, the deep network model is retrained based on the reconstructed training set, and the test images are then classified. Finally, some test images that specific categories cannot distinguish will be assigned to meta-categories to characterize the imprecision in the results. Experiments based on some remarkable networks have shown that RIDL can improve accuracy (AC) and reasonably represent imprecision both in the training and testing sets.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
刚刚
vicky完成签到,获得积分10
3秒前
fiee发布了新的文献求助10
4秒前
哈哈发布了新的文献求助10
4秒前
英俊的铭应助MJQ采纳,获得10
5秒前
7秒前
8秒前
Rhyming完成签到,获得积分20
10秒前
道松先生完成签到,获得积分10
10秒前
pei发布了新的文献求助10
11秒前
SDUMoist完成签到,获得积分10
11秒前
幸福立果完成签到 ,获得积分10
12秒前
香蕉觅云应助Yesyes采纳,获得10
14秒前
fiee完成签到,获得积分10
15秒前
慕青应助小胡采纳,获得10
15秒前
18秒前
18秒前
我是老大应助科研通管家采纳,获得30
19秒前
传奇3应助科研通管家采纳,获得10
19秒前
Jasper应助科研通管家采纳,获得10
19秒前
酷波er应助科研通管家采纳,获得10
19秒前
andrele应助科研通管家采纳,获得10
19秒前
19秒前
19秒前
彭于晏应助科研通管家采纳,获得10
19秒前
19秒前
19秒前
19秒前
19秒前
moncypool发布了新的文献求助10
21秒前
111111发布了新的文献求助10
22秒前
张参完成签到 ,获得积分10
22秒前
22秒前
积极的香菇完成签到 ,获得积分10
23秒前
23秒前
24秒前
25秒前
yk发布了新的文献求助10
26秒前
哈哈哈完成签到,获得积分20
26秒前
lgy发布了新的文献求助10
27秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 2400
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Cognitive Neuroscience: The Biology of the Mind (Sixth Edition) 1000
Optimal Transport: A Comprehensive Introduction to Modeling, Analysis, Simulation, Applications 800
Official Methods of Analysis of AOAC INTERNATIONAL 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3959900
求助须知:如何正确求助?哪些是违规求助? 3506106
关于积分的说明 11127978
捐赠科研通 3238061
什么是DOI,文献DOI怎么找? 1789483
邀请新用户注册赠送积分活动 871803
科研通“疑难数据库(出版商)”最低求助积分说明 803021