In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

As acquiring pixel-wise annotations of real-world images for semantic segmentation is a
costly process, a model can instead be trained with more accessible synthetic data and …

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source
domain (eg synthetic data) to the target domain (eg real-world data) without requiring further …

Multitask learning (MTL) aims to learn multiple tasks simultaneously while exploiting their
mutual relationships. By using shared resources to simultaneously calculate multiple …

Deep neural networks (DNNs) have proven explicit contributions in making autonomous
driving cars and related tasks such as semantic segmentation, motion tracking, object …

In semi-supervised semantic segmentation, a model is trained with a limited number of
labeled images along with a large corpus of unlabeled images to reduce the high annotation …

Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine
learning models trained on a source domain to perform well on unlabeled or even unseen …

Despite the recent advances in multi-task learning of dense prediction problems, most
methods rely on expensive labelled datasets. In this paper, we present a label efficient …

With autonomous industries on the rise, domain adaptation of the visual perception stack is
an important research direction due to the cost savings promise. Much prior art was …

The question of whether pre-training on geometric tasks is viable for downstream transfer to
semantic tasks is important for two reasons, one practical and the other scientific. If the …