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
野椒搞科研发布了新的文献求助200
刚刚
小小蚂蚁发布了新的文献求助10
1秒前
1秒前
zsy完成签到,获得积分10
2秒前
11完成签到,获得积分20
2秒前
小石头发布了新的文献求助10
2秒前
2秒前
Ava应助qaz采纳,获得10
2秒前
科研白菜完成签到,获得积分10
2秒前
张美丽完成签到,获得积分10
2秒前
3秒前
3秒前
4秒前
4秒前
4秒前
彭于晏应助紧张的世德采纳,获得10
4秒前
5秒前
Water应助Brandy采纳,获得10
5秒前
喜欢看夜里的天空完成签到,获得积分20
5秒前
5秒前
今后应助鲍binyu采纳,获得20
5秒前
6秒前
6秒前
6秒前
小皮猪发布了新的文献求助60
7秒前
7秒前
芙瑞发布了新的文献求助30
7秒前
8秒前
谭玲慧发布了新的文献求助10
8秒前
高海龙发布了新的文献求助10
8秒前
高海龙发布了新的文献求助10
8秒前
Fay发布了新的文献求助20
8秒前
搜集达人应助Summer采纳,获得10
9秒前
羌活发布了新的文献求助10
9秒前
高海龙发布了新的文献求助10
9秒前
高海龙发布了新的文献求助10
9秒前
是瓜瓜不发布了新的文献求助10
10秒前
卡牌大师完成签到,获得积分10
10秒前
顾矜应助斯文的若颜采纳,获得10
10秒前
VENTUS完成签到,获得积分10
10秒前
高分求助中
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
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 588
Christian Women in Chinese Society: The Anglican Story 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
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 3961496
求助须知:如何正确求助?哪些是违规求助? 3507837
关于积分的说明 11138394
捐赠科研通 3240311
什么是DOI,文献DOI怎么找? 1790903
邀请新用户注册赠送积分活动 872636
科研通“疑难数据库(出版商)”最低求助积分说明 803288