title: Exploiting causality for efficient Computer Vision
Description: Machine learning approaches for Computer Vision tasks provide remarkable results but are often based on complex architectures requiring huge datasets and massive computations. Efficiency is the challenge we wish to tackle with this project. We will explore how structure in the data distribution can inform the design of novel forms of inductive bias. In particular, we will investigate how causal structure can be used towards this end. The project will be co-supervised by Nicoletta Noceti and Lorenzo Rosasco (UniGe) and Francesco Locatello (Amazon). The time of the student will be shared between the Genova Machine Learning center (MaLGa) and the Amazon AWS labs in Tuebingen.
Research line: Data Science and Engineering.
Topics: Computer Vision, Machine Learning.
Perspective candidates should make an expression of interest before 8/6/2021.