21st – 26th August 2022, Tunis, Tunisia
The Deep Learning Indaba is the annual meeting of the African machine learning community with the mission to strengthen African Machine Learning.
Tuesday, 23rd, 12:00 – 13:30 (GMT+2):
Gabriela Csurka: Keynote: Visual Domain Adaptation in the Deep Learning Era
Abstract: Domain adaptation (DA) is one of the solutions proposed in the literature to overcome the burden of annotation, which is often critical when working with deep neural networks. The main idea is to exploit labelled data or trained models available in related source domains together with unlabelled data from the target domain. The aim of this talk will be to give an overview of visual domain adaptation, a field whose popularity in the computer vision community has increased significantly in the last few years. First, after a short recall of historical shallow methods, I will discuss different DA strategies to exploit deep architectures for visual recognition. Second, I will briefly present a set of deep learning-based trends in the literature to handle domain shift in visual tasks relevant in autonomous driving scenarios, such as image classification and semantic segmentation. I will conclude the talk by integrating visual DA in a larger transfer learning landscape giving some general thoughts about future perspectives in the field.