Collaborative Research: CIF: Medium: Taming Deep Unsupervised Representation Learning in Imaging: Theory and Algorithms
Collaborative Research: CIF: Medium: Taming Deep Unsupervised Representation Learning in Imaging: Theory and Algorithms
批准号:
2212066
负责人:
Qing Qu
金额:
$37.07万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2022
资助国家:
美国
项目状态:
未结题
起止时间:
2022-10-01 至 2025-09-30
中文摘要
深度神经网络正在推动工程和科学应用领域的重大突破。它们的成功往往建立在大量高质量数据集的可用性基础上。然而,对于许多逆问题或分类问题,例如在计算机断层扫描(CT)、磁共振成像(MRI)和冷冻电子显微镜(Cryo-EM)中,获得成对的训练数据可能非常困难或昂贵。训练数据也可能是有限的或严重损坏的。虽然最近的进展通过深度图像先验或自我监督学习等方法解决了这些挑战,但其中的训练过程往往是临时的,这些方法背后的潜在机制远未得到很好的理解,这是由于缺乏精确的数学建模和对学习表示的理解。为了应对这些挑战,该项目旨在通过结合物理模型和约束来有效地捕获内在数据结构和不变性,来开发健壮的无监督深度学习方法,并在数据有限和被破坏的情况下提供严格的保证。开发的方法的实用性将在各种成像应用中得到演示,由此产生的结果和软件将被广泛传播。此外,该项目将开发一个新的教育计划,包括每年一次的全球参与的虚拟研讨会,并有针对性地在密歇根州东南部推广K-12课程,以提高对机器学习和计算计划的参与,特别是来自代表性不足的学生。该项目旨在开发稳健的、无监督的深度表示学习方法,并为其在医学、工业和科学成像中的反问题或分类问题中的应用提供严格的保证。重点将放在从有限和/或损坏的未配对数据中学习深度模型。将设计和学习深层表示,通过利用传统浅层学习方法(例如,词典/变换学习)的思想来捕捉数据的内在结构和低维。通过理解在深度表示学习的不同阶段捕获的图像特征,将结合物理模型、先验和约束,从而使深度网络能够从损坏的数据中高效地学习。深度表示还将被设计为对典型的对称歧义保持不变,例如平移和旋转。基于这样的原则性建模,将开发高效和稳健的优化方法,为学习数据的内在结构提供理论保障,所开发的方法将应用于各种成像问题。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。
英文摘要
Deep neural networks are driving significant breakthroughs across engineering and scientific applications. Their success is often predicated on the availability of large and high-quality data sets. However, for many inverse problems or classification problems such as in computed tomography (CT), magnetic resonance imaging (MRI), and cryo-electron microscopy (cryo-EM), obtaining paired training data can be extremely difficult or expensive. The training data may also be limited or highly corrupted. While recent progress addresses these challenges via methods such as deep image prior or self-supervised learning, the training procedures therein are often ad hoc and the underlying mechanisms behind the approaches are far from well-understood, which are due to the lack of precise mathematical modeling and the lack of understanding of learned representations. To deal with these challenges, this project aims to develop robust unsupervised deep learning methods with rigorous guarantees in settings with limited and corrupted data by incorporating physical models and constraints that capture the intrinsic data structures and invariances effectively. The utility of the developed methods will be demonstrated on a variety of imaging applications, and the resulting findings and software will be widely disseminated. Furthermore, this project will develop a new educational program involving yearly virtual workshops with global participation and targeted K-12 outreach in southeast Michigan to enable improved participation in machine learning and computing programs, especially from underrepresented students.This project aims to develop robust, unsupervised deep representation learning methods with rigorous guarantees for application in inverse problems or classification problems in medical, industrial, and scientific imaging. The focus will be on learning deep models from limited and/or corrupted unpaired data. Deep representations will be designed and learned to capture the intrinsic structures and low-dimensionality of the data by leveraging ideas from traditional shallow learning methods (e.g., dictionary/transform learning). By understanding image characteristics captured during different stages of deep representation learning, physical models, priors, and constraints will be incorporated that enable deep networks to be learned efficiently from corrupted data. The deep representations will also be designed to be invariant to typical symmetry ambiguities such as translations and rotations. Based upon such principled modeling, efficient and robust optimization methods will be developed with theoretical guarantees for learning the intrinsic structures of the data, and the developed methods will be applied to a variety of imaging problems.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.
期刊论文(5)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
DOI:
10.48550/arxiv.2209.09211
发表时间:
2022-09
期刊:
ArXiv
影响因子:
--
作者:
[Can Yaras;Peng Wang;Zhihui Zhu;L. Balzano;Qing Qu]
通讯作者:
Can Yaras;Peng Wang;Zhihui Zhu;L. Balzano;Qing Qu
DOI:
10.48550/arxiv.2210.10041
发表时间:
2022-10
期刊:
ArXiv
影响因子:
--
作者:
[Shuo Xie;Jiahao Qiu;Ankita Pasad;Li Du;Qing Qu;Hongyuan Mei]
通讯作者:
Shuo Xie;Jiahao Qiu;Ankita Pasad;Li Du;Qing Qu;Hongyuan Mei
DOI:
--
发表时间:
2022-02
期刊:
ArXiv
影响因子:
--
作者:
[Sheng Liu;Zhihui Zhu;Qing Qu;Chong You]
通讯作者:
Sheng Liu;Zhihui Zhu;Qing Qu;Chong You
DOI:
10.48550/arxiv.2203.01238
发表时间:
2022-03
期刊:
ArXiv
影响因子:
--
作者:
[Jinxin Zhou-;Xiao Li;Tian Ding;Chong You;Qing Qu;Zhihui Zhu]
通讯作者:
Jinxin Zhou-;Xiao Li;Tian Ding;Chong You;Qing Qu;Zhihui Zhu
DOI:
10.48550/arxiv.2210.02192
发表时间:
2022-10
期刊:
ArXiv
影响因子:
--
作者:
[Jinxin Zhou-;Chong You;Xiao Li;Kangning Liu;Sheng Liu;Qing Qu;Zhihui Zhu]
通讯作者:
Jinxin Zhou-;Chong You;Xiao Li;Kangning Liu;Sheng Liu;Qing Qu;Zhihui Zhu
Collaborative Research: RI: Medium: Principles for Optimization, Generalization, and Transferability via Deep Neural Collapse
-
批准号:2312842
-
项目类别:Standard Grant
-
资助金额:$40.0万
-
财政年份:2023
-
负责人:Qing Qu
-
依托单位:
CAREER: From Shallow to Deep Representation Learning: Global Nonconvex Optimization Theories and Efficient Algorithms
-
批准号:2143904
-
项目类别:Continuing Grant
-
资助金额:$63.33万
-
财政年份:2022
-
负责人:Qing Qu
-
依托单位:
Collaborative Research: CIF: Medium: Foundations of Robust Deep Learning via Data Geometry and Dyadic Structure
-
批准号:2212326
-
项目类别:Continuing Grant
-
资助金额:$47.2万
-
财政年份:2022
-
负责人:Qing Qu
-
依托单位:
国内基金
海外基金
登录
查看更多内容
Research on Quantum Field Theory without a Lagrangian Description
-
批准号:24ZR1403900
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2024
-
负责人:SATOSHI NAWATA
-
依托单位:
Cell Research
-
批准号:31224802
-
项目类别:专项基金项目
-
资助金额:24.0万元
-
批准年份:2012
-
负责人:程磊
-
依托单位:
Cell Research
-
批准号:31024804
-
项目类别:专项基金项目
-
资助金额:24.0万元
-
批准年份:2010
-
负责人:程磊
-
依托单位:
Cell Research (细胞研究)
-
批准号:30824808
-
项目类别:专项基金项目
-
资助金额:24.0万元
-
批准年份:2008
-
负责人:张爱兰
-
依托单位:
Research on the Rapid Growth Mechanism of KDP Crystal
-
批准号:10774081
-
项目类别:面上项目
-
资助金额:45.0万元
-
批准年份:2007
-
负责人:滕冰
-
依托单位: