Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption
(TTA) continues to adapt the model after deployment. Recently, the area of continual and …

Abstract Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the
labeled source domain to an unlabeled target domain. In this paper, we present Prototypical …

Since distribution shifts are likely to occur during test-time and can drastically decrease the
model's performance, online test-time adaptation (TTA) continues to update the model after …

Deep neural networks (DNNs) have proven their capabilities in the past years and play a
significant role in environment perception for the challenging application of automated …

When models, eg, for semantic segmentation, are applied to images that are vastly different
from training data, the performance will drop significantly. Domain adaptation methods try to …

Intelligent sampling from simulation becomes crucial due to storage and hardware
constraints. This research focuses on developing an intelligent acquisition strategy for …

To overcome the domain gap between synthetic and real-world datasets, unsupervised
domain adaptation methods have been proposed for semantic segmentation. Majority of the …

In recent years, there has been tremendous progress in the field of semantic image
segmentation. However, one remaining challenging problem is that segmentation models …

Standard unsupervised domain adaptation methods adapt models from a source to a target
domain using labeled source data and unlabeled target data jointly. In model adaptation, on …

Thanks to its great power in feature representation, deep learning (DL) is widely used in
semantic segmentation tasks. However, the requirements for high distribution consistency of …