Towards a Compositional Generative Model of Human Vision

迈向人类视觉的组合生成模型

基本信息

  • 批准号:
    10228003
  • 负责人:
  • 金额:
    $ 32.45万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
  • 财政年份:
    2019
  • 资助国家:
    美国
  • 起止时间:
    2019-09-30 至 2023-07-31
  • 项目状态:
    已结题

项目摘要

Understanding object recognition has long been a central problem in vision science, because of its applied utility and computational difficulty. Progress has been slow, because of an inability to process complex natural images, where the largest challenges arise. Recently, advances in Deep Convolutional Neural Networks (DCNNs) spurred unprecedented success in natural image recognition. The general goal of this proposal is to leverage this success to test computational theories of human object recognition in natural images. However, DCNNs still markedly underperform humans when challenged with high levels of ambiguity, occlusion, and articulation. We hypothesize that humans' superior performance arises from the use of knowledge about how images and objects are structured. Preliminary evidence for this claim comes from the success of hybrid models, that combine DCNNS for identifying features and parts in images, with explicit knowledge of object and image structure. These computations occur within a hierarchy, which includes both top-down and bottom- up processing. The specific goal of the work proposed here is to strongly test whether these computational strategies, structured, hierarchical representations and bidirectional processing, are used to recognize objects in natural images. Human bodies are composed of hierarchically organized configurable parts, making them an ideal test domain. We examine the complete recognition process, from parts, to pairs of parts, to whole bodies, each in its own aim. Each aim also tests important sub-hypotheses about when and how the computational strategies are used. Aim 1 examines recognition of individual body parts, testing whether it is dependent on parsing images into more basic features and relationships, for example edges and materials. Aim 2 examines pairs of parts, testing the importance of knowledge of body connectedness relationships. Aim 3 examines perception of entire bodies, testing whether knowledge of global body structure guides bidirectional processing. In each aim, we first develop nested computer vision models that either do or do not make use of structural knowledge, to test whether it aids recognition. We then test whether human performance can be accounted for by the availability of that structural knowledge. We next measure neural activity with functional MRI to identify where and how it is used in cortex. Finally, we integrate these results to produce even stronger tests, using the nested models to predict human performance and confusion matrices as well as fMRI activity levels and confusion matrices. Altogether, this work will strongly test key theoretical accounts of object recognition in the most important domain, perception of natural images. The work, based on extensive preliminary data, measures and models the entire body recognition system. The models developed and tested here should surpass the state-of-the-art, and be useful for many real-world recognition tasks. The proposal will also lay the groundwork for future studies of recognition impaired by disease.
理解物体识别一直是视觉科学的核心问题,因为它的应用

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 }}

DANIEL J KERSTEN其他文献

DANIEL J KERSTEN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('DANIEL J KERSTEN', 18)}}的其他基金

Towards a Compositional Generative Model of Human Vision
迈向人类视觉的组合生成模型
  • 批准号:
    10458624
  • 财政年份:
    2019
  • 资助金额:
    $ 32.45万
  • 项目类别:
Towards a Compositional Generative Model of Human Vision
迈向人类视觉的组合生成模型
  • 批准号:
    10018020
  • 财政年份:
    2019
  • 资助金额:
    $ 32.45万
  • 项目类别:
Object Perception Mechanisms for Resolving Ambiguity
解决歧义的对象感知机制
  • 批准号:
    6828206
  • 财政年份:
    2003
  • 资助金额:
    $ 32.45万
  • 项目类别:
Object Perception Mechanisms for Resolving Ambiguity
解决歧义的对象感知机制
  • 批准号:
    6989711
  • 财政年份:
    2003
  • 资助金额:
    $ 32.45万
  • 项目类别:
Object Perception Mechanisms for Resolving Ambiguity
解决歧义的对象感知机制
  • 批准号:
    7171803
  • 财政年份:
    2003
  • 资助金额:
    $ 32.45万
  • 项目类别:
Object Perception Mechanisms for Resolving Ambiguity
解决歧义的对象感知机制
  • 批准号:
    6710204
  • 财政年份:
    2003
  • 资助金额:
    $ 32.45万
  • 项目类别:
VISUAL INFORMATION FOR REACH AND GRASP
便于获取和掌握的视觉信息
  • 批准号:
    2165818
  • 财政年份:
    1996
  • 资助金额:
    $ 32.45万
  • 项目类别:
VISUAL INFORMATION FOR REACH AND GRASP
便于获取和掌握的视觉信息
  • 批准号:
    2888522
  • 财政年份:
    1996
  • 资助金额:
    $ 32.45万
  • 项目类别:
VISUAL INFORMATION FOR REACH AND GRASP
便于获取和掌握的视觉信息
  • 批准号:
    2711184
  • 财政年份:
    1996
  • 资助金额:
    $ 32.45万
  • 项目类别:
VISUAL INFORMATION FOR REACH AND GRASP
便于获取和掌握的视觉信息
  • 批准号:
    2444386
  • 财政年份:
    1996
  • 资助金额:
    $ 32.45万
  • 项目类别:

相似国自然基金

层出镰刀菌氮代谢调控因子AreA 介导伏马菌素 FB1 生物合成的作用机理
  • 批准号:
    2021JJ40433
  • 批准年份:
    2021
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
寄主诱导梢腐病菌AreA和CYP51基因沉默增强甘蔗抗病性机制解析
  • 批准号:
    32001603
  • 批准年份:
    2020
  • 资助金额:
    24.0 万元
  • 项目类别:
    青年科学基金项目
AREA国际经济模型的移植.改进和应用
  • 批准号:
    18870435
  • 批准年份:
    1988
  • 资助金额:
    2.0 万元
  • 项目类别:
    面上项目

相似海外基金

Onboarding Rural Area Mathematics and Physical Science Scholars
农村地区数学和物理科学学者的入职
  • 批准号:
    2322614
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Standard Grant
TRACK-UK: Synthesized Census and Small Area Statistics for Transport and Energy
TRACK-UK:交通和能源综合人口普查和小区域统计
  • 批准号:
    ES/Z50290X/1
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Research Grant
Wide-area low-cost sustainable ocean temperature and velocity structure extraction using distributed fibre optic sensing within legacy seafloor cables
使用传统海底电缆中的分布式光纤传感进行广域低成本可持续海洋温度和速度结构提取
  • 批准号:
    NE/Y003365/1
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Research Grant
Point-scanning confocal with area detector
点扫描共焦与区域检测器
  • 批准号:
    534092360
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Major Research Instrumentation
Collaborative Research: Scalable Manufacturing of Large-Area Thin Films of Metal-Organic Frameworks for Separations Applications
合作研究:用于分离应用的大面积金属有机框架薄膜的可扩展制造
  • 批准号:
    2326714
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Standard Grant
Collaborative Research: Scalable Manufacturing of Large-Area Thin Films of Metal-Organic Frameworks for Separations Applications
合作研究:用于分离应用的大面积金属有机框架薄膜的可扩展制造
  • 批准号:
    2326713
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Standard Grant
Unlicensed Low-Power Wide Area Networks for Location-based Services
用于基于位置的服务的免许可低功耗广域网
  • 批准号:
    24K20765
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
RAPID: Collaborative Research: Multifaceted Data Collection on the Aftermath of the March 26, 2024 Francis Scott Key Bridge Collapse in the DC-Maryland-Virginia Area
RAPID:协作研究:2024 年 3 月 26 日 DC-马里兰-弗吉尼亚地区 Francis Scott Key 大桥倒塌事故后果的多方面数据收集
  • 批准号:
    2427233
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Standard Grant
RAPID: Collaborative Research: Multifaceted Data Collection on the Aftermath of the March 26, 2024 Francis Scott Key Bridge Collapse in the DC-Maryland-Virginia Area
RAPID:协作研究:2024 年 3 月 26 日 DC-马里兰-弗吉尼亚地区 Francis Scott Key 大桥倒塌事故后果的多方面数据收集
  • 批准号:
    2427232
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Standard Grant
RAPID: Collaborative Research: Multifaceted Data Collection on the Aftermath of the March 26, 2024 Francis Scott Key Bridge Collapse in the DC-Maryland-Virginia Area
RAPID:协作研究:2024 年 3 月 26 日 DC-马里兰-弗吉尼亚地区 Francis Scott Key 大桥倒塌事故后果的多方面数据收集
  • 批准号:
    2427231
  • 财政年份:
    2024
  • 资助金额:
    $ 32.45万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了