Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the bui ....Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the building of next generation of computer vision systems to work in open and dynamic environments. This should be able to produce solid benefits to the science, society, and economy of Australian via the application of these advanced intelligent systems.Read moreRead less
Learning to Reason in Reinforcement Learning. Deep Reinforcement Learning (RL) uses deep neural networks to represent and learn optimal decision-making policies for intelligent agents in complex environments. However, most RL approaches require millions of episodes to converge to good policies, making it difficult for RL to be applied in real-world scenarios taking significant resources. This project aims to equip RL with capabilities such as counterfactual reasoning and outcome anticipation to ....Learning to Reason in Reinforcement Learning. Deep Reinforcement Learning (RL) uses deep neural networks to represent and learn optimal decision-making policies for intelligent agents in complex environments. However, most RL approaches require millions of episodes to converge to good policies, making it difficult for RL to be applied in real-world scenarios taking significant resources. This project aims to equip RL with capabilities such as counterfactual reasoning and outcome anticipation to significantly reduce the number of interactions required, improve generalisation, and provide the agent with the capability to consider the cause-effects. These improvements would narrow the gap between AI and human capabilities and broaden the adoption of RL in real-world applications.Read moreRead less
Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the ....Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the primary limitations of deep learning and will greatly increase its practical application to a range of industrial, cultural or health settings.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE190100539
Funder
Australian Research Council
Funding Amount
$408,000.00
Summary
Towards conversational vision-based Artificial Intelligence. This project aims to develop a novel learning framework, Vision-Ask-Answer-Act (V3A). This framework will allow a machine to perform a sequence of actions via a conversation with human users, based on intricate processing of not just visual input, but human-computer verbal exchanges. Artificial intelligence has great potential as a tool for economic productivity and daily tasks. Applications in cars and assistant robots, still in their ....Towards conversational vision-based Artificial Intelligence. This project aims to develop a novel learning framework, Vision-Ask-Answer-Act (V3A). This framework will allow a machine to perform a sequence of actions via a conversation with human users, based on intricate processing of not just visual input, but human-computer verbal exchanges. Artificial intelligence has great potential as a tool for economic productivity and daily tasks. Applications in cars and assistant robots, still in their early days, typically require significant expertise to use effectively. The outcomes of this project will push the boundary of vision-language research to produce a conversational intelligent agent that can be easily used in common situations across industry, transport, the medical sector, and at home.Read moreRead less
Context and Activity Recognition for Personalised Behaviour Recommendation. The Internet of Things (IoT) together with the rising popularity of smartphones opens a new world for many exciting opportunities. The overall goal of this project is to develop new algorithms and data analytical techniques in an IoT environment that can accurately monitor and analyse personalised daily activities on a continuous, real-time basis. The expected result of this project will support many critical application ....Context and Activity Recognition for Personalised Behaviour Recommendation. The Internet of Things (IoT) together with the rising popularity of smartphones opens a new world for many exciting opportunities. The overall goal of this project is to develop new algorithms and data analytical techniques in an IoT environment that can accurately monitor and analyse personalised daily activities on a continuous, real-time basis. The expected result of this project will support many critical applications such as better wellness tracking and lifestyle-related illness prevention, which will be particularly critical to Australia's aging population. This project will also serve as a vehicle to educate and train Australia’s young scholars and engineers.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240100967
Funder
Australian Research Council
Funding Amount
$366,000.00
Summary
Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected o ....Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected outcomes include new paradigms for algorithm design and evaluation, and establishing the problem as a focus of international research. The key practical benefit would be to accelerate the wider deployment of visual perception in applications such as autonomous vehicles, interactive robotics, and video analysis.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220100265
Funder
Australian Research Council
Funding Amount
$417,000.00
Summary
A closed-loop human–agent learning framework to enhance decision making. This project aims to design a foundational human–agent learning framework to augment the decision making process, using reinforcement and closed-loop mechanisms to enable symbiosis between a human and an artificial-intelligence agent. It envisages significant new technologies to promote controllability and efficient and safe exploration of an environment for decision actions – drastically boosting learning effectiveness and ....A closed-loop human–agent learning framework to enhance decision making. This project aims to design a foundational human–agent learning framework to augment the decision making process, using reinforcement and closed-loop mechanisms to enable symbiosis between a human and an artificial-intelligence agent. It envisages significant new technologies to promote controllability and efficient and safe exploration of an environment for decision actions – drastically boosting learning effectiveness and interpretability in decision making. Expected outcomes will benefit national cybersecurity by improving our understanding of vulnerabilities and threats involving decision actions, and by ensuring that human feedback and evaluations can help prevent catastrophic events in explorations of dynamic and complex environments.Read moreRead less
New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project wil ....New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project will develop new robust algorithms to mitigate these shortcomings. It will do so by investigating two new paradigms of kernelisation and polyhedral search, which offer unprecedented theoretical insights into the problem. The outcomes will contribute towards computer vision applications that are more practical and reliable.Read moreRead less
Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently ....Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently learn complex interaction and navigation behaviours that transfer to unseen environments. Our research should benefit new applications in domains of economic and societal importance that are currently too complex, unsafe, and uncertain for robot assistants, such as aged care, advanced manufacturing and domestic robotics.Read moreRead less
Active Visual Navigation in an Unexplored Environment. This project will develop a new method for robotic navigation in which goals can be specified at a much higher level of abstraction than has previously been possible. This will be achieved using deep learning to make informed predictions about a scene layout, and navigating as an active observer in which the predictions informs actions. The outcome will be robotic agents capable of effective and efficient navigation and operation in previous ....Active Visual Navigation in an Unexplored Environment. This project will develop a new method for robotic navigation in which goals can be specified at a much higher level of abstraction than has previously been possible. This will be achieved using deep learning to make informed predictions about a scene layout, and navigating as an active observer in which the predictions informs actions. The outcome will be robotic agents capable of effective and efficient navigation and operation in previously unseen environments, and the ability to control such agents with more human-like instructions. Such capabilities are desirable, and in some cases essential, for autonomous robots in a variety of important application areas including automated warehousing and high-level control of autonomous vehicles. Read moreRead less