Learning from Time

Context and potential impact: With the rise of deep learning, computer vision algorithms have had great success in understanding images and videos. Even so, training these algorithms requires a massive amount of manual annotations, limiting its scalability. Recently, there has been increasing interest in circumventing this limitation through self-supervised learning, where useful information can be learned from the raw data itself. This research has a potential impact in allowing machine learning algorithms to scale beyond the availability of labelled datasets, which is an essential step towards learning in the open world.

Aims and Objectives: In this DPhil project, we are particularly interested in self-supervision from 'time', which we interpret in several directions.

First, we aim to learn from the sequential temporal order of frames in videos. We aim to build upon the intuition that the subject in the video usually moves independently from the background, allowing motion between video frames to be used as a substitute for manual annotations in performing object segmentation. We are also interested in extending this towards related tasks including tracking, depth estimation and optical flow, possibly jointly learning these tasks.

Second, we interpret time in the literal sense. We aim to learn the time an image was taken by reading clocks and more subtle cues in images such as shadows and weather conditions, as well as telling the temporal ordering or relative time between images. We explore several methods for self-supervision, from image's EXIF data to synthetic generators, and aim to demonstrate applications of these tasks.

Novelty of the research methodology: Self-supervised learning is a new field of research. We hope to propose new ways of training models through self-supervision, resulting in more efficient, better performing algorithms. We also hope to propose new tasks and applications in computer vision that have never been achieved previously. In terms of architectural novelty, we are particularly interested in applying attention mechanisms, where the model learns where (in space and/or time) it should 'look' at, within the algorithms where appropriate.

Alignment to EPSRC's strategies and research areas: Artificial Intelligence, Image & Vision Computing

Any companies or collaborators involved: N/A

AIMS's impact will be felt across domains of acute need within the UK. We expect AIMS to benefit: UK economic performance, through start-up creation; existing UK firms, both through research and addressing skills needs; UK health, by contributing to cancer research, and quality of life, through the delivery of autonomous vehicles; UK public understanding of and policy related to the transformational societal change engendered by autonomous systems.

Autonomous systems are acknowledged by essentially all stakeholders as important to the future UK economy. PwC claim that there is a £232 billion opportunity offered by AI to the UK economy by 2030 (10% of GDP). AIMS has an excellent track record of leadership in spinout creation, and will continue to foster the commercial projects of its students, through the provision of training in IP, licensing and entrepreneurship. With the help of Oxford Science Innovation (investment fund) and Oxford University Innovation (technology transfer office), student projects will be evaluated for commercial potential.

AIMS will also concretely contribute to UK economic competitiveness by meeting the UK's needs for experts in autonomous systems. To meet this need, AIMS will train cohorts with advanced skills that span the breadth of AI, machine learning, robotics, verification and sensor systems. The relevance of the training to the needs of industry will be ensured by the industrial partnerships at the heart of AIMS. These partnerships will also ensure that AIMS will produce research that directly targets UK industrial needs. Our partners span a wide range of UK sectors, including energy, transport, infrastructure, factory automation, finance, health, space and other extreme environments.

The autonomous systems that AIMS will enable also offer the prospect of epochal change in the UK's quality of life and health. As put by former Digital Secretary Matt Hancock, "whether it's improving travel, making banking easier or helping people live longer, AI is already revolutionising our economy and our society." AIMS will help to realise this potential through its delivery of trained experts and targeted research. In particular, two of the four Grand Challenge missions in the UK Industrial Strategy highlight the positive societal impact underpinned by autonomous systems. The "Artificial Intelligence and data" challenge has as its mission to "Use data, Artificial Intelligence and innovation to transform the prevention, early diagnosis and treatment of chronic diseases by 2030". To this mission, AIMS will contribute the outputs of its research pillar on cancer research. The "Future of mobility" challenge highlights the importance the autonomous vehicles will have in making transport "safer, cleaner and better connected." To this challenge, AIMS offers the world-leading research of its robotic systems research pillar.

AIMS will further promote the positive realisation of autonomous technologies through direct influence on policy. The world-leading academics amongst AIMS's supervisory pool are well-connected to policy formation e.g. Prof Osborne serving as a Commissioner on the Independent Commission on the Future of Work. Further, Dr Dan Mawson, Head of the Economy Unit; Economy and Strategic Analysis Team at BEIS will serve as an advisor to AIMS, ensuring bidirectional influence between policy objectives and AIMS research and training.

Broad understanding of autonomous systems is crucial in making a society robust to the transformations they will engender. AIMS will foster such understanding through its provision of opportunities for AIMS students to directly engage with the public. Given the broad societal importance of getting autonomous systems right, AIMS will deliver core training on the ethical, governance, economic and societal implications of autonomous systems.