A Transfer Learning-Based Multi-Instance Learning Method With Weak Labels

计算机科学 学习迁移 任务(项目管理) 多任务学习 人工智能 机器学习 构造(python库) 集合(抽象数据类型) 负迁移 传输(计算) 过程(计算) 感应转移 趋同(经济学) 半监督学习 机器人学习 经济增长 移动机器人 经济 第一语言 并行计算 哲学 管理 程序设计语言 操作系统 机器人 语言学
作者
Yanshan Xiao,Fei Liang,Bo Liu
出处
期刊:IEEE transactions on cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:52 (1): 287-300 被引量:33
标识
DOI:10.1109/tcyb.2020.2973450
摘要

In multi-instance learning (MIL), labels are associated with bags rather than the instances in the bag. Most of the previous MIL methods assume that each bag has the actual label in the training set. However, from the process of labeling work, the label of a bag is always evaluated by the calculation of the labels obtained from a number of labelers. In the calculation, the weight of each labeler is always unknown and people always assign the weight for each labeler by random or equally, and this may result in the ambiguous labels for the bags, which is called weak labels here. In addition, we always meet the problem of knowledge transfer from the source task to the target task, and this leads to the study of multiple instance transfer learning. In this article, we propose a new framework called transfer learning-based multiple instance learning (TMIL) framework to address the problem of multiple instance transfer learning in which both the source task and the target task contain the weak labels. We first construct a TMIL model with weak labels, which can transfer knowledge from the source task to the target task where both source and target tasks contain weak labels. We then put forward an iterative framework to solve the transfer learning model with weak labels so that we can update the label of the bag to improve the performance of multiple instance learning. We then present the convergence analysis of the proposed method. The experiments show that the proposed method outperforms the existing multiple instance learning methods and can correct the initial labels to obtain the actual labels for the bags.
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
李爱国的应助被科研通管家采纳,获得10
刚刚
脑洞疼的应助被科研通管家采纳,获得10
刚刚
Maestro_S的应助被科研通管家采纳,获得10
刚刚
刚刚
上官若男的应助被科研通管家采纳,获得10
刚刚
刚刚
科目三的应助被Mason采纳,获得30
1秒前
华仔的应助被科研通管家采纳,获得10
1秒前
1秒前
Owen的应助被科研通管家采纳,获得10
1秒前
1秒前
顾矜的应助被科研通管家采纳,获得10
1秒前
FashionBoy的应助被郝子凯采纳,获得10
1秒前
Jasper的应助被科研通管家采纳,获得10
1秒前
大模型的应助被科研通管家采纳,获得30
1秒前
1秒前
整齐从蓉发布了新的文献求助10
2秒前
无花果的应助被科研通管家采纳,获得10
2秒前
2秒前
2秒前
汉堡包的应助被科研通管家采纳,获得10
2秒前
syvshc的应助被科研通管家采纳,获得10
2秒前
聪明机器猫完成签到,获得积分10
2秒前
2秒前
脑洞疼的应助被科研通管家采纳,获得10
2秒前
2秒前
积极问晴完成签到,获得积分10
2秒前
2秒前
SciGPT的应助被科研通管家采纳,获得10
2秒前
2秒前
英姑的应助被科研通管家采纳,获得10
3秒前
酷波er的应助被科研通管家采纳,获得30
3秒前
3秒前
3秒前
3秒前
4秒前
4秒前
5秒前
5秒前
5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
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
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
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 8187652
求助须知:如何正确求助?哪些是违规求助? 9575758
关于积分的说明 21842805
捐赠科研通 7785538
什么是DOI,文献DOI怎么找? 3435073
关于科研通互助平台的介绍 2559480
邀请新用户注册赠送积分活动 2481963