董 豪

姓  名:
董 豪
职  称:
助理教授
研究领域:
深度学习、生成模型、计算机视觉
通信地址:
静园五院106-2
电  话:
+86 (0)10 6275-6561
电子邮件:
hao.dong@pku.edu.cn
个人主页:

http://zsdonghao.github.io

  董豪目前是北京大学信息科学与技术学院前沿计算研究中心的助理教授。他博士于2019年秋从英国帝国理工毕业,师从郭毅可教授。他的研究涉及深度学习和计算机视觉,旨在降低学习智能系统所需要的数据需求。此外,他致力于开源并成立TensorLayer开源框架,获得了ACM Multimedia 2017年度最佳开源软件奖。在博士之前,他分别年从英国帝国理工和英国中央兰开夏大学获得一等研究生和一等本科学位。他与郭毅可教授在2012至2014年共同创办过数字医疗健康方向的公司。

深度学习、生成模型、计算机视觉

Books

 

H. Dong, Y. Guo, G. Yang, “Deep Learning using TensorLayer (深度学习:一起玩转 TensorLayer)”, Publishing House of Electronics Industry. ISBN:9787121326226. 2018[Amazon][JD][Broadview][Code][Organization][Documentation]

• A. Supratak, C. Wu, H. Dong, K. Sun and Y. Guo, “Survey on Feature Extraction and Applications of Biosignals. Machine Learning for Health Informatics”, Springer International Publishing, 161-182. 2016. [Springer]

 

Journals

 

H. Dong, Z. Wei, C. Wu, Y. Guo, “Dropping Activation Outputs with Localized First-layer Deep Network for Enhancing User Privacy and Data Security”, IEEE Trans. Information Forensics and Security (TIFS) IF:5.82. 2017.

• G. Yang, S. Yu, H. Dong, G. Slabaugh, P.L. Dragotti, X. Ye, F. Liu, S. Arridge, J. Keegan, Y. Guo, D. Firmin, “DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction”, IEEE Trans. Medical Imaging (TMI) IF:6.13. 2017. [Code]

H. Dong, A. Supratak, W. Pan, P.M. Matthews, Y. Guo, “Mixed Neural Network Approach for Sleep Stage Classification”, IEEE Trans. on Neural Systems and Rehabilitation Engineering (TNSRE) IF:3.97. 2017.

• A. Supratak, H. Dong, C. Wu, Y. Guo, “DeepSleepNet: A Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG”, IEEE Trans. on Neural Systems and Rehabilitation Engineering (TNSRE) IF:3.97. 2017. [Code]

 

Conferences

 

H. Dong, S. Yu, C. Wu, Y. Guo, “Semantic Image Synthesis via Adversarial Learning”, Int. Conf. on Computer Vision (ICCV). 2017.

H. Dong, A. Supratak, L. Mai, F. Liu, A. Oehmichen, S. Yu, Y. Guo, “TensorLayer: A Versatile Library for Efficient Deep Learning Development”, ACM Multimedia (ACMMM). 2017.

H. Dong, J. Qing, D. McIlwraith, Y. Guo, “I2T2I: Learning Text to Image Synthesis with Textural Data Augmentation”, Int. Conf. on Image Processing (ICIP). 2017. (Oral)

H. Dong, F. Liu, Y. Mo, G. Yang, Y. Guo, “Automatic Brain Tumor Detection and Segmentation using U-Net Based Fully Convolutional Networks”, Medical Image Understanding and Analysis (MIUA). 2017. (Oral)

• S. Yu, H. Dong, P. Wang, C. Wu, Y. Guo, “Generative Creativity: Adversarial Learning for Bionic Design”, Neural Inform. Process. System (NIPS-W) Workshop. 2018.

• A. Supratak, S. Schneider. H. Dong, L. Li, Y. Guo, “Towards Desynchronization Detection in Biosignals”, Neural Inform. Process. System (NIPS-W) Time Series Workshop. 2017.

H. Dong, P.M. Matthews, Y. Guo, “A New Soft Material Based In-The-Ear EEG Recording Technique”, IEEE Engineering in Medicine and Biology Society (EMBC). 2016. (Oral)

• S. Zhang, H. Dong, W. Hu, Y. Guo, C. Wu, D. Xie, F. Wu, “Text-to-Image Synthesis via Visual-Memory Creative Adversarial Network”, Pacific-Rim Conf. on Multimedia (PCM), 2018.

• F. Liu, A. Oehmichen, J. Zhang, K. Sun, H. Dong, Y. Mo, Y. Guo, “TensorDB: Database Infrastructure for Continuous Machine Learning”, Int. Conf. Artificial Intelligence (ICAI). 2017.

• Z. Yao, H. Dong, F. Liu, Y. Guo, “Conditional Image Synthesis Using Stacked Auxiliary Classifier Generative Adversarial Networks”, Future of Information and Communication Conference (FICC). 2018.

 

Technical Reports

 

• S. Yu, H. Dong, G. Yang, G Slabaugh, P.L. Dragotti, X. Ye, F. Liu, S. Arridge, J. Keegan, D. Firmin, Y. Guo, “Deep De-Aliasing for Fast Compressive Sensing MRI”, arXiv:1705.07137. 2017.

H. Dong, P. Neekhara, C. Wu, Y. Guo, “Unsupervised Image-to-Image Translation with Generative Adversarial Networks”, arXiv:1701.02676. 2017.

• W. Pan, H. Dong, Y. Guo, “DropNeuron: Simplifying the Structure of Deep Neural Networks”, arXiv:1606.07326. 2016.

Deep Generative Models (Spring Term 2020)

 

Study and Practice on Topics of Frontier Computing (I) (Autumn Term 2019)

 

Introduction to Deep Learning (Turing Class) (Summer Term 2019)

课题组名称

超平面实验室

 

课题组简介

我们研究方向主要涉及深度/机器学习和计算机视觉,及机器人和医疗健康中的应用。我们的研究设计深度学习和计算机视觉,目的是降低学习智能系统所需要的数据。目前的研究方向包括:

 

• 非监督场景理解:学习世界的表达
• 生成模型与强化学习:学习与世界交互
• 生成模型与计算机视觉:学习看世界

 

课题组链接

https://cfcs.pku.edu.cn/research/project/236578.htm