权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

BIGDATA: IA: Distributed Semi-Supervised Training of Deep Models and Its Applications in Video Understanding

BIGDATA：IA：深度模型的分布式半监督训练及其在视频理解中的应用

基本信息

批准号：
1741431
负责人：
Mubarak Shah
金额：
$ 66.24万
依托单位：
The University of Central Florida Board of Trustees
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-09-01 至 2020-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1741431&HistoricalAwards=false
关键词：
BIGDATA IA Distributed Semi Supervised

项目摘要

This project investigates semi-supervised training of deep neural network models using large-scale labeled and unlabeled data in a distributed fashion. Deep neural networks have recently been widely deployed in artificial intelligence and related scientific fields, largely attributing to well-labeled big datasets and improved computing capabilities. However, the unlabeled data, which is often bigger, is inherently ruled out by the prevailing supervised training of the deep models. It is indeed highly challenging to model the unlabeled parts of many recent and emerging datasets, which are often unstructured and distributed over different nodes of a network (e.g., the videos captured by a camera network). This project aims to explore how to effectively use the unlabeled and distributed data to complement the discriminative cues of the labeled data, to jointly learn accurate and robust deep models. The research seamlessly unifies machine learning, computer vision, and parallel computing, and fosters unique interdisciplinary research and education programs for the graduate and undergraduate students.Despite the progress on semi-supervised learning and deep learning, the confluence of these two is mostly studied on a small scale in single-machine environment. However, many new datasets easily grow beyond the computation or even storage capacity of a single machine. Hence, it becomes a pressing need to investigate the semi-supervised learning of deep models on parallel computing platforms. To better account for this scenario, this project develops improved network architectures to facilitate the parallel training, and the training procedure developed adaptively switches between synchronized and asynchronized modes for optimal efficiency. The main idea is to incorporate a parametric distribution to the neural network and use covariate matching to coordinate the network behaviors across different machines. The researchers also explore a novel application, extreme-scale spatial-temporal action annotation of video sequences, to benchmark the algorithms and frameworks in this project.

该项目以分布式方式研究使用大规模标记和未标记数据的深度神经网络模型的半监督训练。近年来，深度神经网络在人工智能和相关科学领域得到了广泛应用，这主要归功于标记良好的大数据集和改进的计算能力。然而，未标记的数据通常更大，本质上被主流的深度模型监督训练排除在外。对许多最新和新兴数据集的未标记部分进行建模确实非常具有挑战性，这些数据集通常是非结构化的，分布在网络的不同节点上（例如，由摄像机网络捕获的视频）。本项目旨在探索如何有效地利用未标记和分布式数据来补充标记数据的判别线索，共同学习准确和鲁棒的深度模型。该研究将机器学习、计算机视觉和并行计算无缝地结合起来，为研究生和本科生培养了独特的跨学科研究和教育项目。尽管在半监督学习和深度学习方面取得了进展，但这两者的融合研究大多是在单机环境下的小规模研究。然而，许多新数据集的增长很容易超出单个机器的计算甚至存储容量。因此，研究并行计算平台上深度模型的半监督学习成为一个迫切需要。为了更好地考虑这种情况，该项目开发了改进的网络架构来促进并行训练，并开发了自适应的训练过程，在同步和异步模式之间切换，以实现最佳效率。其主要思想是将参数分布纳入神经网络，并使用协变量匹配来协调不同机器之间的网络行为。研究人员还探索了一种新的应用，即视频序列的极端尺度时空动作注释，以对该项目中的算法和框架进行基准测试。

项目成果

期刊论文数量（21）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

DOI：
发表时间：
2019-05
期刊：
ArXiv
影响因子：
0
作者：
Yandong Li;Lijun Li;Liqiang Wang;Tong Zhang;Boqing Gong
通讯作者：
Yandong Li;Lijun Li;Liqiang Wang;Tong Zhang;Boqing Gong

Learning a Multi-concept Video Retrieval Model with Multiple Latent Variables

DOI：
10.1145/3176647
发表时间：
2016-12
期刊：
2016 IEEE International Symposium on Multimedia (ISM)
影响因子：
0
作者：
Amir Mazaheri;Boqing Gong;M. Shah
通讯作者：
Amir Mazaheri;Boqing Gong;M. Shah

Photography and Exploration of Tourist Locations Based on Optimal Foraging Theory

DOI：
10.1109/tcsvt.2019.2915103
发表时间：
2020-07-01
期刊：
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
影响因子：
8.4
作者：
Rawat, Yogesh Singh;Shah, Mubarak;Kankanhalli, Mohan S.
通讯作者：
Kankanhalli, Mohan S.

Select to Better Learn: Fast and Accurate Deep Learning Using Data Selection From Nonlinear Manifolds

选择更好地学习：使用非线性流形中的数据选择进行快速准确的深度学习

DOI：
10.1109/cvpr42600.2020.00784
发表时间：
2020
期刊：
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR
影响因子：
0
作者：
Joneidi, Mohsen;Vahidian, Saeed;Esmaeili, Ashkan;Wang, Weijia;Rahnavard, Nazanin;Lin, Bill;Shah, Mubarak
通讯作者：
Shah, Mubarak

Training Faster by Separating Modes of Variation in Batch-Normalized Models