Machine Learning prerequisites
** : Good skills

Python prerequisites
** : Good skills

Technical prerequisites
Bring your own laptop

Speakers
This workshop will be animated by :

• Denis Marraud, Image Processing Senior Expert, Airbus Defence and Space

Workshop overview
Following the Frugal AI overview workshop organized in May, this next workshop will aim at putting in practice and comparing the interest of some relevant Frugal AI techniques to solve a domain adaptation problem for one or several image semantic segmentation tasks. The cost and complexity of dense annotations required for this task makes it particularly interesting to leverage any technique contributing to the reduction of the number of required manual annotations.
Envisaged techniques may include advanced data augmentation and pseudo-labelling methods, weakly supervised or self-supervised methods. Various domain adaptation tasks may be considered : either domain specialization (or transductive learning) where the test domain is known in advance and closed, domain extension where the performance should be optimized for both source and target domain, or domain adaptation where the performance should be optimized on the target domain only.

Dataset description
Extracts from publicly available image segmentation datasets will be delivered to the participants. These datasets will cover various application domains such as medical imagery, satellite or aerial imagery and self driving car imagery.

Algorithmic methods
Among the techniques that could be tested during this workshop :

• Advanced data augmentation methods (based on existing libraries)
• Advanced pseudo-labelling methods (making use of non annotated data)
• Self-supervised methods (e.g. contrastive learning, predictive learning) as a pre-training step
• Test time adaptation methods to adapt to local context