ADR Awareness Centre

we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data.

We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes.

pygrank is an open source framework to define, run and evaluate node ranking algorithms.

InDistill enchances the effectiveness of the Knowledge Distillation procedure by leveraging the properties of channel pruning to both reduce the capacity gap between the models and retain the information geometry.

Inspired by scenario writing methods to foster discussion on the societal implications of technology and regulation, the paper develops a ‘legal fiction scenario’ to anticipate the impact of the proposed European 

The project aimed to implement fair automatic recognition by offering guidance in policy development on an European and national level.