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
For more information, please visit: https://zsdonghao.github.io/
|Deep Learning, Generative Models, Computer Vision
1. Unsupervised World Modelling
Enabling machines to understand the world in human-like approaches in an important topic in AI and cognitive science. Interactive environments include controllable agent and other objects; we achieve an action-label free approach to model the interaction between the agent and the physical environment, enabling action-based visual forecasting.
Specifically, humans are talented at modelling the real-world physical environment from visual observations. The environment is driven forward by the control of the agent and the interaction between the agent and the environment. By observing an agent interacting with the environment, humans develop senses of interaction laws in the environment, thus acquiring the ability to control the agent and predict events happen in the future, which helps them to make decisions and perform actions.
For example, one of our research studies the problem of modelling the environment. Although existing methods achieve impressive results training with action supervision, environment modelling from only visual observations still remains challenging. One of our study proposes an end-to-end method that learns to identify the agent within a deterministic environment using only visual observations (videos) as the training data. Then, for each action, only one demonstration that shows the transition caused by the action is applied to model the interaction between the agent and environment.
2. Generative + Computer Vision
Controllable data generation is important to computer vision and machine learning. We study how to use less supervision to achieve various generative tasks, such as unsupervised image-to-image translation and natural language image manipulation. Those researches are important to both domain adaptation and generation models.
For example, one of our study disentangles the semantic information from the two modalities (image and text) and generate new images from the combined semantics. Another study proposes a new method to replace cycle loss and successfully perform geometric changes, remove large objects, or ignore irrelevant texture.
3. Digital Healthcare
For health care, we study how to use less data and low-cost sensors to achieve better diagnostic performance. Our researches reduce the scanning time of MRI, reduce the data required for tumour segmentation and sleep scoring. Specifically, we design new algorithms for MRI reconstruction and new algorithms for MRI tumor segmentation. Apart from medical imaging, we also have research related to other data modality. For example, another previous direction designs new soft material and electrode for in-the-ear EEG recoding and single-channel EEG analysis method for low-cost sleep stage scoring.