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

• 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

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.

该项目研究以分布式方式使用大规模标记和未标记数据对深度神经网络模型进行半监督训练。深度神经网络最近在人工智能和相关科学领域得到了广泛部署，很大程度上归功于标记良好的大数据集和计算能力的提高。然而，未标记的数据通常更大，本质上被流行的深度模型监督训练所排除。对许多最近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并且分布在网络的不同节点上（例如，摄像机网络捕获的视频）。该项目旨在探索如何有效地利用未标记的分布式数据来补充标记数据的判别线索，共同学习准确且鲁棒的深度模型。该研究无缝地统一了机器学习、计算机视觉和并行计算，并为研究生和本科生培育了独特的跨学科研究和教育项目。尽管半监督学习和深度学习取得了进展，但这两者的融合主要集中在以下方面：小规模的单机环境。然而，许多新数据集很容易超出单台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以促进并行训练，并且开发的训练程序自适应地在同步和异步模式之间切换以获得最佳效率。主要思想是将参数分布合并到神经网络中，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颖的应用，即视频序列的超大规模时空动作注释，以对该项目中的算法和框架进行基准测试。

项目成果

Semi Supervised Semantic Segmentation Using Generative Adversarial Network

使用生成对抗网络的半监督语义分割

• DOI: 10.1109/iccv.2017.606
• 发表时间: 2017-10-01
• 期刊: 2017 IEEE International Conference on Computer Vision (ICCV)
• 作者: Nasim Souly;C. Spampinato;M. Shah
• 通讯作者: M. Shah

Visual Text Correction

视觉文本校正

• DOI: 10.1007/978-3-030-01261-8_10
• 发表时间: 2018-01-06
• 作者: Amir Mazaheri;M. Shah
• 通讯作者: M. Shah

How Local Is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization

当地的多样性有多本地化？

• DOI: 10.1007/978-3-030-01237-3_10
• 发表时间: 2018-01
• 期刊: Computer Vision - ECCV 2018
• 作者: Li, Y.;Wang, L.;Yang, T.;Gong, B.
• 通讯作者: Gong, B.

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

NATTACK：学习对抗样本的分布以改进深度神经网络的黑盒攻击

• 发表时间: 2019-01
• 期刊: Proceedings of Machine Learning Research
• 作者: Li, Yandong;Li, Lijun;Wang, Liqiang;Zhang, Tong;Gong, Boqing
• 通讯作者: Gong, Boqing

Photography and Exploration of Tourist Locations Based on Optimal Foraging Theory

基于最优觅食理论的旅游地摄影与探索

• 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: Y. Rawat;M. Shah;M. Kankanhalli
• 通讯作者: M. Kankanhalli