CCSS: Uncertainty-Aware Computational Imaging in the Wild: a Bayesian Deep Learning Approach in the Latent Space

CCSS:野外不确定性感知计算成像:潜在空间中的贝叶斯深度学习方法

基本信息

  • 批准号:
    2318758
  • 负责人:
  • 金额:
    $ 20万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2023
  • 资助国家:
    美国
  • 起止时间:
    2023-08-15 至 2023-10-31
  • 项目状态:
    已结题

项目摘要

From microscopy and tomography to biometrics and surveillance, computational imaging (CI) has greatly expanded mankind’s vision capability in various scientific and engineering fields. In contrast to hardware-based solutions that require expensive optics, data-driven or computational approaches powered by deep learning have fueled the development of AI-enabled computational imaging systems. The emerging paradigm of Bayesian deep learning endows the next-generation CI systems more flexibility to handle various uncertainties in the wild – no matter whether they are related to the adversarial conditions of image acquisition (e.g., moving platform or bad weather) or unintentional mistakes made by humans (e.g., the mal-functioned main mirror of Hubble Space Telescope after the launch into the space). Developing uncertainty-aware CI systems have a wide range of impact on both scientific exploration (e.g., imaging at extreme scales such as microscopic and astronomical) and our daily lives (e.g., smartphone applications).This project aims at taking a Bayesian deep learning (BDL) approach to modeling uncertainty in real-world imaging scenarios. An important new insight brought about by this project is to unify the flow-based uncertainty kernel estimation (for likelihood modeling) with memory-based uncertainty image generation in latent space (for prior modeling). Under a fully Bayesian framework but using reparameterization to simplify the modeling process, the proposed BDL greatly facilitates both degradation learning and image reconstruction in the realistic scenario when uncertainty is inevitable. The proposed research consists of three tasks: 1) Flow-based Nonuniform Kernel Estimation in the Latent Space; 2) Memory-enhanced Deep Generative Models for Image Reconstruction; and 3) Real-world Applications in Deep Tissue Imaging such as Superresolution Microscopy.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
从显微镜和层析成像到生物特征识别和监视,计算成像(CI)极大地扩展了人类在各个科学和工程领域的视觉能力。与需要昂贵光学设备的基于硬件的解决方案相比,深度学习支持的数据驱动或计算方法推动了支持人工智能的计算成像系统的发展。贝叶斯深度学习的新兴范式赋予下一代CI系统更大的灵活性,以处理野外的各种不确定性-无论这些不确定性是与图像获取的不利条件(例如,移动的平台或恶劣天气)有关,还是与人类犯下的无意错误(例如,哈勃太空望远镜在发射进入太空后出现故障)有关。开发不确定性感知的CI系统对科学探索(例如,极端尺度的成像,如显微镜和天文)和我们的日常生活(例如,智能手机应用程序)都有广泛的影响。该项目旨在采用贝叶斯深度学习(BDL)的方法来建模真实世界成像场景中的不确定性。该项目带来的一个重要的新见解是将基于流的不确定性核估计(用于似然建模)和基于记忆的潜在空间不确定性图像生成(用于先验建模)统一起来。在完全贝叶斯框架下,通过重新参数化简化建模过程,在不确定性不可避免的真实场景中,BDL极大地方便了退化学习和图像重建。建议的研究包括三个任务:1)潜在空间中基于流的非均匀核估计;2)记忆增强的深度生成图像重建模型;3)在深度组织成像中的真实应用,如超分辨率显微镜。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。

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 }}

Xin Li其他文献

Performance Characters of OLTP in CMP
CMP 中 OLTP 的性能特征
Importance of series elasticity in a powered transtibial prosthesis with ankle and toe joints
串联弹性在带踝关节和脚趾关节的动力跨胫骨假体中的重要性
Observations of pores and surrounding regions with CO 4.66 micron lines by BBSO/CYRA
通过 BBSO/CYRA 用 CO 4.66 微米线观察孔隙和周围区域
  • DOI:
    10.1051/0004-6361/202244600
  • 发表时间:
    2022-11
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yongliang Song;Xianyong Bai;Xu Yang;Wenda Cao;Han Uitenbroek;Yuanyong Deng;Xin Li;Xiao Yang;Mei Zhang
  • 通讯作者:
    Mei Zhang
A tumor map generated from three-dimensional visualization of image fusion for the assessment of microwave ablation of hepatocellular carcinoma: a preliminary study
图像融合三维可视化生成的肿瘤图用于评估肝细胞癌微波消融:初步研究
  • DOI:
    10.2147/cmar.s195354
  • 发表时间:
    2019-02
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Chao An;Xin Li;Ping liang;Jie Yu;Zhigang Cheng;Zhiyu Han;Fangyi Liu;Linan Dong
  • 通讯作者:
    Linan Dong
The effectiveness of guideline to improve intercultural sensitivity in cross-cultural management
跨文化管理中提高跨文化敏感性指南的有效性

Xin Li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('Xin Li', 18)}}的其他基金

HCC: Small: Toward Computational Modeling of Autism Spectrum Disorder: Multimodal Data Collection, Fusion, and Phenotyping
HCC:小型:自闭症谱系障碍的计算模型:多模式数据收集、融合和表型分析
  • 批准号:
    2401748
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
CCSS: Uncertainty-Aware Computational Imaging in the Wild: a Bayesian Deep Learning Approach in the Latent Space
CCSS:野外不确定性感知计算成像:潜在空间中的贝叶斯深度学习方法
  • 批准号:
    2348046
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
CAREER:Single-neuron mechanisms of social attention in humans
职业:人类社会注意力的单神经元机制
  • 批准号:
    2401398
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Continuing Grant
AF: Small: Fundamental Questions in Communication and Computation Regarding Edit Type String Measures
AF:小:有关编辑类型字符串测量的通信和计算的基本问题
  • 批准号:
    2127575
  • 财政年份:
    2021
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
HCC: Small: Toward Computational Modeling of Autism Spectrum Disorder: Multimodal Data Collection, Fusion, and Phenotyping
HCC:小型:自闭症谱系障碍的计算模型:多模式数据收集、融合和表型分析
  • 批准号:
    2114644
  • 财政年份:
    2021
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
CAREER:Single-neuron mechanisms of social attention in humans
职业:人类社会注意力的单神经元机制
  • 批准号:
    1945230
  • 财政年份:
    2020
  • 资助金额:
    $ 20万
  • 项目类别:
    Continuing Grant
CAREER: Pseudorandom Objects and their Applications in Computer Science
职业:伪随机对象及其在计算机科学中的应用
  • 批准号:
    1845349
  • 财政年份:
    2019
  • 资助金额:
    $ 20万
  • 项目类别:
    Continuing Grant
SHF: Small: Re-thinking Polynomial Programming: Efficient Design and Optimization of Resilient Analog/RF Integrated Systems by Convexification
SHF:小:重新思考多项式编程:通过凸化实现弹性模拟/射频集成系统的高效设计和优化
  • 批准号:
    1720569
  • 财政年份:
    2017
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
SHF: Small: Re-thinking Polynomial Programming: Efficient Design and Optimization of Resilient Analog/RF Integrated Systems by Convexification
SHF:小:重新思考多项式编程:通过凸化实现弹性模拟/射频集成系统的高效设计和优化
  • 批准号:
    1604150
  • 财政年份:
    2016
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
AF: Small: Randomness in Computation - Old Problems and New Directions
AF:小:计算中的随机性 - 老问题和新方向
  • 批准号:
    1617713
  • 财政年份:
    2016
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant

相似海外基金

CAREER: Uncertainty-aware sensing and management for IoT
职业:物联网的不确定性感知传感和管理
  • 批准号:
    2340049
  • 财政年份:
    2024
  • 资助金额:
    $ 20万
  • 项目类别:
    Continuing Grant
Cross-Layer Uncertainty-Aware Reinforcement Learning for Safe Autonomous Driving
用于安全自动驾驶的跨层不确定性感知强化学习
  • 批准号:
    EP/Y002644/1
  • 财政年份:
    2024
  • 资助金额:
    $ 20万
  • 项目类别:
    Research Grant
Climate Tipping Points: Uncertainty-aware quantification of Earth system tipping potential from observations and models and assessment of associated climatic, ecological, and socioeconomic impacts
气候临界点:通过观测和模型以及对相关气候、生态和社会经济影响的评估,对地球系统潜在的不确定性进行量化
  • 批准号:
    10090795
  • 财政年份:
    2024
  • 资助金额:
    $ 20万
  • 项目类别:
    EU-Funded
Uncertainty aware virtual treatment planning for peripheral pulmonary artery stenosis
外周肺动脉狭窄的不确定性虚拟治疗计划
  • 批准号:
    10734008
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
CCSS: Uncertainty-Aware Computational Imaging in the Wild: a Bayesian Deep Learning Approach in the Latent Space
CCSS:野外不确定性感知计算成像:潜在空间中的贝叶斯深度学习方法
  • 批准号:
    2348046
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Uncertainty-aware full-body motion planning of aerial and multi-legged robots for urban search and rescue operations
用于城市搜救行动的空中和多足机器人的不确定性全身运动规划
  • 批准号:
    560791-2020
  • 财政年份:
    2022
  • 资助金额:
    $ 20万
  • 项目类别:
    Alliance Grants
Dependable Predictive Inference with Uncertainty-Aware Machine Learning
通过不确定性感知机器学习进行可靠的预测推理
  • 批准号:
    2210637
  • 财政年份:
    2022
  • 资助金额:
    $ 20万
  • 项目类别:
    Continuing Grant
Uncertainty Quantification for Probabilistic Stability Analysis and Uncertainty-Aware Control of Electric Power Systems
电力系统概率稳定性分析和不确定性感知控制的不确定性量化
  • 批准号:
    RGPIN-2022-03236
  • 财政年份:
    2022
  • 资助金额:
    $ 20万
  • 项目类别:
    Discovery Grants Program - Individual
III: Medium: Collaborative Research: MUDL: Multidimensional Uncertainty-Aware Deep Learning Framework
III:媒介:协作研究:MUDL:多维不确定性感知深度学习框架
  • 批准号:
    2107449
  • 财政年份:
    2021
  • 资助金额:
    $ 20万
  • 项目类别:
    Continuing Grant
Uncertainty-aware full-body motion planning of aerial and multi-legged robots for urban search and rescue operations
用于城市搜救行动的空中和多足机器人的不确定性全身运动规划
  • 批准号:
    560791-2020
  • 财政年份:
    2021
  • 资助金额:
    $ 20万
  • 项目类别:
    Alliance Grants
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了