Unsupervised Object Learning

The Context and Potential Impact
Computer vision has progressed significantly in the last decade. Deep learning has enabled the detection of diverse objects, understanding scene layouts, and even captioning them with great accuracy. Much of the current work is supervised, requiring vast amounts of manually labelled data to learn. However, humans can easily understand basic visual concepts by observation alone, and reason in high-level terms such as objects and their relationships. This makes learning object-centric representation from unlabelled data an important area with high impact, promising to alleviate the need for labour-intensive dataset annotation and enable higher-level object-centric reasoning in downstream applications.
Novelty of Research Methodology
Some attempts have been made towards understanding scenes in an unsupervised manner. However, prior work is primarily limited to single objects tasks, such as saliency detection or foreground-background separation. The real-world comprises multiple objects in complex arrangements. Only very recently, some approaches have explored the unsupervised multi-object setting. However, these models work with synthetic inputs featuring simple 2D or 3D shapes. It is not clear how to apply this to the complex natural world. This research, on the other hand, explores learning multiple object-centric representations in an unsupervised manner, in complex settings.
Aims and Objective
Short term goals revolve around investigating and developing methods applicable to visually intricate scenes. Initial work will concentrate on unsupervised scene segmentation problems, i.e., recognising to which object a pixel belongs. Long term goals include exploring the role of video, stereo vision and 3D scene representations to enable object-centric scene understanding.
Alignment to EPSRC's Strategies and RAs
This project belongs to EPSRC's Artificial intelligence technologies and Image and vision computing research areas.

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.