Unlock the Future of Medical AI with the Kvasir-VQA Dataset
We aim to benchmark the Kvasir-VQA dataset across various cutting-edge tasks. As a student, you have the flexibility to choose one or multiple tasks that align with your interests and focus your research efforts accordingly.
Are you passionate about AI, machine learning, and the potential to revolutionise healthcare? Join us at the forefront of medical innovation, where you can explore the latest in medical AI, like large language models (LLMs) and diffusion models. We aim to benchmark the Kvasir-VQA dataset across various cutting-edge tasks. As a student, you have the flexibility to choose one or multiple tasks that align with your interests and focus your research efforts accordingly. You'll have the opportunity to experiment with and evaluate the latest models, identifying those that outperform existing benchmarks. Your work will involve not only applying state-of-the-art techniques but also innovating by finding and testing newer models that can push the boundaries of what's possible in medical AI.
Goal
This unique dataset is formatted as visual question-answer pairs, making it an ideal resource for a variety of applications, including:
- Visual Question Answering (VQA)
- Image Captioning
- Synthetic Medical Image Generation
With this project, you’ll have the opportunity to work on real-world challenges in medical AI, contributing to advancements that could save lives and shape the future of healthcare.
Learning outcome
- Master AI & Machine Learning: Dive deep into the latest advancements in LLMs and explore their applications in healthcare.
- Cutting-Edge Research Skills: Develop and refine research methodologies to assess the effectiveness of contrastive learning and other state-of-the-art techniques.
- Publication Opportunities: Learn the ropes of writing and publishing scientific papers, setting the stage for a successful academic or industry career.
Qualifications
- Eager to Learn: You're excited about exploring new technologies and methodologies.
- Proficient in Python: You have a solid foundation in Python programming and are ready to tackle complex challenges.
- Driven and Committed: You bring a strong work ethic and a passion for making a real impact in the field of medical AI.
- (Additional skills and knowledge can be developed throughout the thesis work.)
Supervisors
- Vajira Thambawita
- Sushant Gautam
- Pål Halvorsen
- Michael Riegler
