Abstract Domain adaptive semantic segmentation aims to adapt a model trained on labeled
source domain to the unlabeled target domain. Self-training shows competitive potential in …

This paper addresses an interesting yet challenging problem--source-free unsupervised
domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation--given only a …

In this paper, we address the challenging source-free unsupervised domain adaptation
(SFUDA) for pinhole-to-panoramic semantic segmentation, given only a pinhole image pre …

Abstract Unsupervised Domain Adaptation (UDA) aims to solve the problem of label scarcity
of the target domain by transferring the knowledge from the label rich source domain …

Abstract Domain generalization semantic segmentation methods aim to generalize well on
out-of-distribution scenes, which is crucial for real-world applications. Recent works focus on …

Source-free domain adaptation has developed rapidly in recent years, where the well-
trained source model is adapted to the target domain instead of the source data, offering the …

Robust semantic segmentation under adverse conditions is crucial in real-world
applications. To address this challenging task in practical scenarios where labeled normal …

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 …

This paper studies a practical Source-free unsupervised domain adaptation (SFUDA)
problem, which transfers knowledge of source-trained models to the target domain, without …

Semantic segmentation is a fundamental and crucial task that is of great importance to real-
world satellite image-based applications. Yet a widely acknowledged issue that occurs …