Supervised learning tasks require a huge amount of annotated data, that is usually hard and expensive to label.
Current advancements in computer vision are moving the field toward a category of algorithms called self-supervised learning, for learning visual representations directly from unsupervised data. The goal of these techniques is to leverage non-labelled data and learn key visual representations that are useful and transferable to a set of supervised tasks.
The goal of this thesis is to investigate current algorithms for learning visual representations using self-supervised approaches, and apply them to both unsupervised and supervised tasks like anomaly detection, video action detection, and objects detection, with a low annotated-data regime.
- Research current self-supervised learning algorithms for computer vision.
- Develop the most promising self-supervised algorithms.
- Apply, evaluate, and benchmark the developed algorithms on a set of downstream tasks.
Who we’re looking for
Students that are about to get their Master Degree in: Computer Science, Computer Engineering, Mechatronic Engineering, Electronic
Engineering, Mathematical Engineering, Mathematics, Physics.
Skills: Proficiency in Python; Basic knowledge of Machine learning and Deep learning; Experience with at least one Deep learning framework (e.g. TensorFlow, Pytorch); Good knowledge of linear algebra.
Duration of this Projects: 6-8 months