Non-convex Variational Image Processing: Boosting Classical Methods with Machine Learning

非凸变分图像处理：通过机器学习增强经典方法

• 批准号: 1912866
• 负责人: Thomas Goldstein
• 金额: $ 19.82万
• 依托单位: University of Maryland, College Park
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-01 至 2022-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1912866&HistoricalAwards=false
• 关键词: Non; convex; Variational; Image; Processing

Recent advances in machine learning and AI, particularly those based on artificial neural networks, have enabled us to build systems that solve difficult information processing problems with human-like accuracy. For example, neural networks can recognize objects, predict how proteins fold, automate manufacturing processing, and use computer vision to navigate a vehicle or analyze satellite imagery. Unfortunately, these advanced AI systems come with their own unique problems. Like humans, neural networks can behave erratically, sometimes making strange and unexplainable decisions when asked to perform tasks that differ even a little from their training. For this reason, classifical image and signal processing methods are still the go-to solution when reliability, interpretability, and computational speed at needed. The goal of this research project is to mash up the performance and power of neural networks with the speed and reliability and classical algorithms. This research project also features an integrated teaching plan involving graduate students and undergraduate interns. To achieve this goal, we consider three interrelated research thrusts. First, we consider ways that deep networks can help to automate and improve classical algorithms. For example, networks can be used to automate the selection of hyper-parameters, choose objective functions to minimize, identify noise types and levels that are present in data, and make other decisions that are needed to optimally tune the performance of classical imaging system. Second, we consider ways that neural networks can be 'plugged in' to classical variational imaging methods. For example, classical image priors (such as wavelet sparsity or total variation), can be replaced with more sophisticated priors defined by neural networks. Third, we consider efficient algorithms for solving minimization problems that arise when complex neural networks are used as components in classical optimization problems. Better algorithms will allow us to solve these complex problems efficiently, and without human oversight. This new suite of approaches has the potential to improve that state of the art for a range of important practical problems that have been studied by the PI. This includes enhancing deblurring problems of the type used for microscopy of new materials, boosting segmentation algorithms used to identify faults in semiconductor manufacturing, and solving complex resource allocation problems for medical applications.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.

机器学习和人工智能的最新进展，特别是那些基于人工神经网络的技术，使我们能够构建系统，以类似人类的精度解决困难的信息处理问题。 例如，神经网络可以识别物体，预测蛋白质如何折叠，自动化制造过程，并使用计算机视觉来导航车辆或分析卫星图像。不幸的是，这些先进的人工智能系统都有自己独特的问题。 像人类一样，神经网络也会表现得不稳定，有时候当被要求执行与训练略有不同的任务时，会做出奇怪且无法解释的决定。因此，当需要可靠性、可解释性和计算速度时，分类图像和信号处理方法仍然是首选解决方案。 本课题的目标是将神经网络的性能和能力与经典算法的速度和可靠性相结合。该研究项目还包括一个涉及研究生和本科实习生的综合教学计划。为了实现这一目标，我们考虑三个相互关联的研究重点。 首先，我们考虑深度网络可以帮助自动化和改进经典算法的方法。 例如，网络可以用于自动选择超参数，选择目标函数以最小化，识别数据中存在的噪声类型和水平，以及做出最佳调整经典成像系统性能所需的其他决策。 其次，我们考虑的方式，神经网络可以“插入”到经典的变分成像方法。例如，经典的图像先验（如小波稀疏性或全变分）可以用神经网络定义的更复杂的先验来代替。第三，我们认为有效的算法来解决最小化问题时出现的复杂神经网络被用作经典优化问题的组件。 更好的算法将使我们能够有效地解决这些复杂的问题，而无需人为监督。这套新的方法有可能改善PI研究的一系列重要实际问题的最新技术水平。这包括增强用于新材料显微镜检查的去模糊问题，提高用于识别半导体制造故障的分割算法，以及解决医疗应用中复杂的资源分配问题。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响评审标准进行评估，被认为值得支持。

项目成果

MSE-Optimal Neural Network Initialization via Layer Fusion

• DOI: 10.1109/ciss48834.2020.1570617381
• 发表时间: 2020-01
• 期刊: 2020 54th Annual Conference on Information Sciences and Systems (CISS)
• 作者: Ramina Ghods;Andrew S. Lan;T. Goldstein;Christoph Studer

Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates

• 发表时间: 2020-03
• 期刊: ArXiv
• 作者: Amin Ghiasi;Ali Shafahi;T. Goldstein

MetaPoison: Practical General-purpose Clean-label Data Poisoning

• 发表时间: 2020-04
• 期刊: ArXiv
• 作者: W. R. Huang;Jonas Geiping;Liam H. Fowl;Gavin Taylor;T. Goldstein

Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective

神经网络可以学习同一模型两次吗？

• DOI: 10.1109/cvpr52688.2022.01333
• 发表时间: 2022
• 期刊: CVPR
• 作者: Somepalli, Gowthami;Fowl, Liam;Bansal, Arpit;Yeh-Chiang, Ping;Dar, Yehuda;Baraniuk, Richard;Goldblum, Micah;Goldstein, Tom
• 通讯作者: Goldstein, Tom

GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training

• 发表时间: 2021-02
• 期刊: ArXiv
• 作者: Chen Zhu;Renkun Ni;Zheng Xu;Kezhi Kong;W. R. Huang;T. Goldstein