+86 (0)10 6275-6561
hao.dong
Room 106-2, Courtyard No.5, Jingyuan
Embodied AI, Robotics, Computer Vision https://zsdonghao.github.io/Bio-Sketch
Dr. Hao Dong joined Peking University in August 2019 and is currently an assistant professor at Center on Frontiers of Computing Studies, PKU. He obtained a Ph.D. degree from Imperial College London under the supervision of Yike Guo in Fall 2019. His research involves robotics, reinforcement learning and computer vision with the goal of reducing the data required for learning intelligent systems. He is passionate about popularizing artificial intelligence technologies and established TensorLayer, a deep learning and reinforcement learning library for scientists and engineers, which won the Best Open Source Software Award at ACM Multimedia 2017. Before Ph.D., he received a MSc specialist degree with distinction from Imperial, and a first-class BEng degree from the University of Central Lancashire. He founded a start-up for digital healthcare with Yike Guo between 2012 and 2014.
Publications
Books
■ Deep Reinforcement Learning: Fundamentals, Research and Applications
Hao Dong, Zihan Ding, Shanghang Zhang Eds.
Springer 2020 ISBN 978-981-15-4094-3, 1st ed.
深度强化学习：基础、研究与应用 董豪 丁子涵 仉尚航 等著（中文译本）
电子工业出版社 2021 ISBN: Coming Soon. [Homepage] [Springer] [免费中文在线] [京东]
■ Deep Learning using TensorLayer (深度学习：一起玩转TensorLayer)
Hao Dong, Yike Guo, Guang Yang et al
Publishing House of Electronics Industry（电子工业出版社）2018 ISBN: 9787121326226. [Amazon] [京东] [Broadview] [Code] [Organisation] [Documentation]
■ Survey on Feature Extraction and Applications of Biosignals
Akara Supratak, Chao Wu, Hao Dong, Kai Sun, Yike Guo
Machine Learning for Health Informatics, Springer, Page 161-182 2016. [Springer]
Recent Papers
■ Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
Haoqi Yuan, Ruihai Wu, Andrew Zhao, Haipeng Zhang, Zihan Ding, Hao Dong
arXiv 2103.04301. [Paper] [Code]
■ End-to-End Object Detection with Adaptive Clustering Transformer
Minghang Zheng, Peng Gao, Xiaogang Wang, Hongsheng Li, Hao Dong
arXiv 2011.09315. [Paper] [Code]
■ P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding
Yunze Liu, Li Yi, Shanghang Zhang, Qingnan Fan, Thomas Funkhouser, Hao Dong
arXiv 2012.13089. [Paper] [Code]
■ Generative 3D Part Assembly via Dynamic Graph Learning
Jialei Huang*, Guanqi Zhan*, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas Guibas, Hao Dong
NeurIPS 2020. [Paper] [Code] [Project]
■ ACL-GAN: Unpaired Image-to-Image Translation using Adversarial Consistency Loss
Yihao Zhao, Ruihai Wu, Hao Dong
European Conference on Computer Vision (ECCV) 2020. [Paper] [Code]
■ Lyapunov-Based Reinforcement Learning for Decentralized Multi-Agent Control
Qingrui Zhang, Hao Dong and Wei Pan
Int. Conf. on Distributed Artificial Intelligence (DAI) 2020 (Oral). [Paper]
■ Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification
Chu-ran Wang*, Jing Li*, Fandong Zhang, Xinwei Sun, Hao Dong, Yizhou Yu, and Yizhou Wang
arXiv:2009.14406 2020. [Paper]
■ RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library
Zihan Ding, Tianyang Yu, Yanhua Huang, Hongming Zhang, Luo Mai, Hao Dong
arXiv:2009.08644 2020. [Paper] [Code]
■ Role-Wise Data Augmentation for Knowledge Distillation
Jie Fu, Xue Geng, Zhijian Duan, Bohan Zhuang, Xingdi Yuan, Adam Trischler, Jie Lin, Chris Pal, Hao Dong
arXiv-2004.08861 2020. [Paper] [Code]
Before 2020
■ DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation
Guanqi Zhan, Yihao Zhao, Bingchan Zhao, Haoqi Yuan, Baoquan Chen, Hao Dong
arXiv:1911.09943 2019. [Paper]
■ An Artificial Intelligence Based Data-driven Approach for Design Ideation
Liuqing Chen, Pan Wang, Hao Dong, Feng Shi, Ji Han, Yike Guo, Peter RN Childs, Jun Xiao, Chao Wu
Journal of Visual Communication and Image Representation 2019. [Paper]
■ SIMGAN: Photo-Realistic Semantic Image Manipulation Using Generative Adversarial Networks
Simiao Yu, Hao Dong, Felix Liang, Yuanhan Mo, Chao Wu, Yike Guo
Int. Conf. on Image Processing (ICIP) 2019 (Oral). [Paper]
■ Conditional Image Synthesis Using Stacked Auxiliary Classifier Generative Adversarial Networks
Zhongwei Yao, Hao Dong, Pan Wang, Chao Wu, Yike Guo
Future of Information and Communications Conference (FICC) 2018. [Paper]
■ Generative Creativity: Adversarial Learning for Bionic Design
Simiao Yu, Hao Dong, Pan Wang, Chao Wu, Yike Guo
Neural Inform. Process. Systems (NeurIPS) Workshop 2018. [Paper]
■ Text-to-Image Synthesis via Visual-Memory Creative Adversarial Network
Shengyu Zhang, Hao Dong, Wei Hu, Yike Guo, Chao Wu, Di Xie, Fei Wu
Pacific Rim Conference on Multimedia (PCM) 2018. [Paper]
■ Dropping Activation Outputs with Localized First-layer Deep Network for Enhancing User Privacy and Data Security
Hao Dong, Chao Wu, Wei Zhen, Yike Guo
IEEE Trans. on Inform. Forensics and Security (TIFS) 2018. [Paper]
■ Towards Desynchronisation Detection in Biosignals
Akara Supratak, Steffen Schneider, Hao Dong, Ling Li, Yike Guo
Neural Inform. Process. Systems (NeurIPS) Time Series Workshop 2017. [Paper] [Project]
■ SisGAN: Semantic Image Synthesis via Adversarial Learning
---Image Manipulation with Natural Language
Hao Dong*, Simiao Yu*, Chao Wu, Yike Guo
Int. Conf. on Computer Vision (ICCV) 2017. [Paper]
■ TensorLayer: A Versatile Library for Efficient Deep Learning Development
Hao Dong, Akara Supratak, Luo Mai, Fangde Liu, Axel Oehmichen, Simiao Yu, Yike Guo
ACM Multimedia (MM) 2017 (Winner of the Best Open Source Software Award). [Paper] [Code] [Organisation] [Documentation]
■ DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction
Guang Yang*, Simiao Yu*, Hao Dong, Greg Slabaugh, Pier Luigi Dragotti, Xujiong Ye, Fangde Liu, Simon Arridge, Jennifer Keegan, Yike Guo, David Firmin
IEEE Trans. Med. Imag. (TMI) 2017. [Paper] [Code]
■ Deep De-Aliasing for Fast Compressive Sensing MRI
Simiao Yu*, Hao Dong*, Guang Yang, Greg Slabaugh, Pier Luigi Dragotti, Xujiong Ye, Fangde Liu, Simon Arridge, Jennifer Keegan, David Firmin, Yike Guo
arXiv:1705.07137 2017. [Paper]
■ I2T2I: Learning Text to Image Synthesis with Textual Data Augmentation
Hao Dong, Jingqing Zhang, Douglas McIlwraith, Yike Guo
Int. Conf. on Image Processing (ICIP) 2017 (Oral). [Paper] [Code]
■ Unsupervised Image-to-Image Translation with Generative Adversarial Networks
Hao Dong, Paarth Neekhara, Chao Wu, Yike Guo
arXiv:1701.02676 2017. [Paper] [Code]
■ DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
Akara Supratak, Hao Dong, Chao Wu, Yike Guo
IEEE Trans. on Neural Systems and Rehabilitation Eng. (TNSRE) 2017. [Paper] [Code]
■ Mixed Neural Network Approach for Temporal Sleep Stage Classification
Hao Dong, Akara Supratak, Wei Pan, Chao Wu, Paul M Matthews, Yike Guo
IEEE Trans. on Neural Systems and Rehabilitation Eng. (TNSRE) 2017. [Paper]
■ Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks
Hao Dong, Guang Yang, Fangde Liu, Yuanhan Mo, Yike Guo
Medical Image Understanding and Analysis (MIUA) 2017 (Oral). [Paper]
■ TensorDB: Database Infrastructure for Continuous Machine Learning
Fangde Liu, Axel Oehmichen, Jingqing Zhang, Kai Sun, Hao Dong, Yuanman Mo, Yike Guo
Int. Conf. Artificial Intelligence (ICAI) 2017. [Paper]
■ A New Soft Material based In-the-Ear EEG Recording Technique
Hao Dong, Paul M Matthews, Yike Guo
Int. Eng. in Medicine and Biology Conf. (EMBC) 2016 (Oral). [Paper]
■ DropNeuron: Simplifying the Structure of Deep Neural Networks
Wei Pan, Hao Dong, Yike Guo
arXiv:1606.07326 2016. [Paper] [Code]
Research Lab
Name
Hyperplane Lab
Introduction
The primary research interests are in the fields of Deep/Machine Learning and Computer Vision, with broader interests in Digital Healthcare and Robotics. Our goal is to reduce the data required for learning intelligent systems. The current topics include:
• Unsupervised World Modelling: learning the representation of the world
• Generative + Reinforcement Learning: learning to interact with the world
• Generative + Computer Vision: learning to see the world
Link: