Towards Open-world Semi-supervised learning
走向开放世界的半监督学习
基本信息
- 批准号:2766068
- 负责人:
- 金额:--
- 依托单位:
- 依托单位国家:英国
- 项目类别:Studentship
- 财政年份:2022
- 资助国家:英国
- 起止时间:2022 至 无数据
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Large amounts of fully annotated data is one of the major components responsible for the success of current deep-learning models. However, in many application scenarios, this assumption of having an extensive collection of human provided annotations is not realistic, as gathering those annotations can be costly and require expert knowledge. Additionally in real-world settings, new concepts and categories may emerge over time. Thus it is often not feasible to gather human annotations for every possible concept. This project will focus on the question of how to build autonomous agents that can automatically reason about novel categories for which no human supervision is provided at training time.Current semi-supervised learning methods are limited in that they require all categories to have human annotations for at least one example. As a result it can be hard to directly adopt previous semi-supervised learning methods in this open-world regime. Recently a new area called Novel Category Discovery (NCD) has emerged, which is closely related to this project, which focuses on the problem of how to discover novel categories within a large unlabelled dataset by leveraging knowledge from an existing labelled dataset. However, NCD methods assume that all the categories in the unlabelled set are novel, and only focus on the performance of those novel categories.In a real-world scenario, it is of equal importance to be able to recognise both previously seen categories as well as discover novel ones. In this work, we aim to develop algorithms and solutions for open-world semi-supervised learning. The developed algorithms will not only be able to recognise previously seen categories using labelled and unlabelled data, but also be able to discover novel categories from unlabelled data. Upon successful development of these new methods, we also aim to design interpretable methods that can convey 'why' the model thinks a set of examples are novel and `how' a newly discovered novel category differs from previously seen ones. These proposed interpretable methods will give new insight into large unlabeled image collections and will advance current deep-learning approaches into a more realistic open-world setting. In this project, we will focus on the following goals: (1) Classifier learning: Learning to classify both seen and novel categories using labelled and unlabelled images.(2) Category number estimation: The category number estimation algorithm should be able to run efficiently and be performed simultaneously with the classifier learning process.(3) Interpreting discovered categories: Interpretable model outputs so that the user knows why some images are predicted to form a novel category.To design novel methods for this new open-world semi-supervised learning setting, we aim to draw inspiration from classic unsupervised clustering methods and cutting-edge deep learning methods:(1) Hierarchical clustering, these methods have the advantage of automatically merging data points to adaptively form a hierarchy of categories, by learning a similarity measuring function using neural networks. We can leverage it to perform hierarchical clustering and to be able to learn the classifier and estimate the number of novel categories at the same time.(2) Leveraging state-of-the-art visual-language models, we also aim to use recent advancements in visual-language learning to design methods for automatically generating a textual explanation for interpreting 'why' the model thinks a set of examples are novel, and 'how' the novel categories differ from the 'seen' categories from the human labelled dataset.We will apply these methods to real-world tasks to better understand the practical challenges present which will inform the development of more robust models.
大量完全注释的数据是当前深度学习模型成功的主要组成部分之一。然而,在许多应用场景中,具有大量人类提供的注释的这种假设是不现实的,因为收集这些注释可能是昂贵的并且需要专业知识。此外,在现实世界中,新的概念和类别可能会随着时间的推移而出现。因此,为每个可能的概念收集人类注释通常是不可行的。这个项目将集中在如何建立自主代理的问题,可以自动推理的新类别,没有人的监督提供在training time.当前的半监督学习方法是有限的,因为他们需要所有类别有人类注释至少一个例子。因此,在这个开放的世界中,很难直接采用以前的半监督学习方法。最近出现了一个新的领域,称为新的类别发现(NCD),这是密切相关的这个项目,其重点是如何发现新的类别在一个大型的未标记的数据集中,利用知识从现有的标记数据集的问题。然而,NCD方法假设未标记集合中的所有类别都是新的,并且只关注那些新类别的性能。在现实世界中,能够识别先前看到的类别以及发现新类别同样重要。在这项工作中,我们的目标是开发开放世界半监督学习的算法和解决方案。开发的算法不仅能够使用标记和未标记的数据识别以前见过的类别,而且还能够从未标记的数据中发现新的类别。在成功开发这些新方法后,我们还旨在设计可解释的方法,这些方法可以传达“为什么”模型认为一组示例是新颖的,以及“如何”新发现的新颖类别与以前看到的不同。这些提出的可解释方法将为大型未标记图像集提供新的见解,并将当前的深度学习方法推进到更现实的开放世界环境中。在这个项目中,我们将专注于以下目标:(1)分类器学习:学习使用标记和未标记的图像对可见和新类别进行分类。(2)类别数量估计:类别数估计算法应该能够有效地运行,并与分类器学习过程同时执行。(3)解释发现的类别:可解释的模型输出,使用户知道为什么一些图像被预测为形成一个新的类别。为了为这种新的开放世界半监督学习环境设计新颖的方法,我们的目标是从经典的无监督聚类方法和尖端的深度学习方法中汲取灵感:(1)层次聚类,这些方法具有自动合并数据点以自适应地形成类别的层次的优点,通过使用神经网络学习相似性测量函数。我们可以利用它来执行层次聚类,并能够学习分类器,同时估计新类别的数量。(2)利用最先进的视觉语言模型,我们还旨在利用视觉语言学习的最新进展来设计自动生成文本解释的方法,以解释“为什么”模型认为一组示例是新颖的,以及新类别与人类标记数据集的“见过”类别“如何不同。我们将把这些方法应用于真实的-世界任务是更好地了解当前的实际挑战,这将为开发更强大的模型提供信息。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
其他文献
吉治仁志 他: "トランスジェニックマウスによるTIMP-1の線維化促進機序"最新医学. 55. 1781-1787 (2000)
Hitoshi Yoshiji 等:“转基因小鼠中 TIMP-1 的促纤维化机制”现代医学 55. 1781-1787 (2000)。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
LiDAR Implementations for Autonomous Vehicle Applications
- DOI:
- 发表时间:
2021 - 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
吉治仁志 他: "イラスト医学&サイエンスシリーズ血管の分子医学"羊土社(渋谷正史編). 125 (2000)
Hitoshi Yoshiji 等人:“血管医学与科学系列分子医学图解”Yodosha(涉谷正志编辑)125(2000)。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
Effect of manidipine hydrochloride,a calcium antagonist,on isoproterenol-induced left ventricular hypertrophy: "Yoshiyama,M.,Takeuchi,K.,Kim,S.,Hanatani,A.,Omura,T.,Toda,I.,Akioka,K.,Teragaki,M.,Iwao,H.and Yoshikawa,J." Jpn Circ J. 62(1). 47-52 (1998)
钙拮抗剂盐酸马尼地平对异丙肾上腺素引起的左心室肥厚的影响:“Yoshiyama,M.,Takeuchi,K.,Kim,S.,Hanatani,A.,Omura,T.,Toda,I.,Akioka,
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('', 18)}}的其他基金
An implantable biosensor microsystem for real-time measurement of circulating biomarkers
用于实时测量循环生物标志物的植入式生物传感器微系统
- 批准号:
2901954 - 财政年份:2028
- 资助金额:
-- - 项目类别:
Studentship
Exploiting the polysaccharide breakdown capacity of the human gut microbiome to develop environmentally sustainable dishwashing solutions
利用人类肠道微生物群的多糖分解能力来开发环境可持续的洗碗解决方案
- 批准号:
2896097 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
A Robot that Swims Through Granular Materials
可以在颗粒材料中游动的机器人
- 批准号:
2780268 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
Likelihood and impact of severe space weather events on the resilience of nuclear power and safeguards monitoring.
严重空间天气事件对核电和保障监督的恢复力的可能性和影响。
- 批准号:
2908918 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
Proton, alpha and gamma irradiation assisted stress corrosion cracking: understanding the fuel-stainless steel interface
质子、α 和 γ 辐照辅助应力腐蚀开裂:了解燃料-不锈钢界面
- 批准号:
2908693 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
Field Assisted Sintering of Nuclear Fuel Simulants
核燃料模拟物的现场辅助烧结
- 批准号:
2908917 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
Assessment of new fatigue capable titanium alloys for aerospace applications
评估用于航空航天应用的新型抗疲劳钛合金
- 批准号:
2879438 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
Developing a 3D printed skin model using a Dextran - Collagen hydrogel to analyse the cellular and epigenetic effects of interleukin-17 inhibitors in
使用右旋糖酐-胶原蛋白水凝胶开发 3D 打印皮肤模型,以分析白细胞介素 17 抑制剂的细胞和表观遗传效应
- 批准号:
2890513 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
Understanding the interplay between the gut microbiome, behavior and urbanisation in wild birds
了解野生鸟类肠道微生物组、行为和城市化之间的相互作用
- 批准号:
2876993 - 财政年份:2027
- 资助金额:
-- - 项目类别:
Studentship
相似国自然基金
精子发生中mRNA下游开放阅读框(downstream Open Reading Frame,dORF)的功能研究
- 批准号:
- 批准年份:2022
- 资助金额:54 万元
- 项目类别:面上项目
基于升阶谱方法和Open CASCADE的高阶网格自动生成技术研究
- 批准号:11972004
- 批准年份:2019
- 资助金额:62.0 万元
- 项目类别:面上项目
基于Linked Open Data的Web服务语义互操作关键技术
- 批准号:61373035
- 批准年份:2013
- 资助金额:77.0 万元
- 项目类别:面上项目
变分与拓扑方法和Schrodinger方程中的Open 问题
- 批准号:10871109
- 批准年份:2008
- 资助金额:23.0 万元
- 项目类别:面上项目
相似海外基金
能動的Open-world認識による知識拡張・環境認識基盤の構築
通过主动的开放世界识别扩展知识并构建环境识别基础设施
- 批准号:
24H00733 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Scientific Research (A)
Unifying Object Detection and Image Captioning using Vision-Language Knowledge Base for Open-World Comprehension
使用视觉语言知识库统一对象检测和图像描述以实现开放世界理解
- 批准号:
24K20830 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Early-Career Scientists
Open Access Block Award 2024 - World Conservation Monitoring Cen WCMC
2024 年开放获取区块奖 - 世界保护监测中心 WCMC
- 批准号:
EP/Z533087/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
Open-world computer vision by detecting and tracking hierarchical objects
通过检测和跟踪分层对象来实现开放世界计算机视觉
- 批准号:
DE240100967 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Discovery Early Career Researcher Award
CAREER: Towards Open World Event Knowledge Extraction with Weak Supervision
职业:在弱监督下实现开放世界事件知识提取
- 批准号:
2238940 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Continuing Grant
NeuroWellbeing Immersive Tech: AI-enabled, Augmented-Reality, 3D open world, immersive educational mobile games
NeuroWellbeing沉浸式技术:人工智能、增强现实、3D开放世界、沉浸式教育手机游戏
- 批准号:
10054612 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Collaborative R&D
Collaborative Research: III: Small: Taming Large-Scale Streaming Graphs in an Open World
协作研究:III:小型:在开放世界中驯服大规模流图
- 批准号:
2236578 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Standard Grant
Open Access Block Award 2023 - World Conservation Monitoring Cen WCMC
2023 年开放获取区块奖 - 世界保护监测中心 WCMC
- 批准号:
EP/Y530013/1 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Research Grant
Growing the world's largest shared infrastructure in space, the Open Constellation
发展世界上最大的太空共享基础设施——开放星座
- 批准号:
10066140 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Collaborative R&D
CAREER: Visual Learning in an Open and Continual World
职业:开放和持续世界中的视觉学习
- 批准号:
2239292 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Continuing Grant