Unsupervised Scene Understanding

Lead Research Organisation: University of Oxford


Brief Description of the Context of the Research Including Potential Impact
Visual reasoning is a crucial problem with wide-ranging applications in autonomous vehicles, robotics, and content editing. A large part of the current work relies on vast amounts of manually annotated data. However, humans and other animals can understand the world from visual observations alone, and for example reason about objects and object parts, and how they are related with no explicit supervision. The purpose of this research is to explore how various scene understanding tasks can be done in an unsupervised manner. Understanding the world without supervision is an important area with a large impact as it can remove the need for expensive annotated datasets and might be easier to scale.

Aims and Objectives
Our goal is to explore the potential of large pretrained models in understanding visual scenes without the need for explicit labels. We aim to explore various cross-modal models, both generative and discriminative, and develop novel ways of using them to perform visual reasoning tasks. We aim to tackle a large range of tasks - semantic correspondences, semantic segmentation, referring expressions comprehension. In addition, we aim to explore and introduce novel tasks that bridge different modalities, such as vision and language.

Novelty of the Research Methodology
While large pretrained models have shown promise in various machine learning tasks, their potential in unsupervised scene understanding remains largely untapped. We plan to publish our results in top-tier computer vision conferences, and will also make our code, models, and datasets open-source to encourage further development and research in this area.

Alignment to EPSRC's Strategies and Research Areas
This project aligns with the EPSRC research areas of Artificial Intelligence Technologies, Image and Vision Computing, and Information Systems.

Planned Impact

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.


10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S024050/1 30/09/2019 30/03/2028
2420422 Studentship EP/S024050/1 30/09/2020 29/09/2024 Aleksandar Shtedritski