Recent semantic segmentation models perform well under standard weather conditions and
sufficient illumination but struggle with adverse weather conditions and nighttime. Collecting …

Adaptation of semantic segmentation networks to different visual conditions is vital for robust
perception in autonomous cars and robots. However, previous work has shown that most …

The performance of nighttime semantic segmentation has been significantly improved
thanks to recent unsupervised methods. However, these methods still suffer from complex …

Data generation is recognized as a potent strategy for unsupervised domain adaptation
(UDA) pertaining semantic segmentation in adverse weathers. Nevertheless, these adverse …

Autonomous driving needs to ensure all-weather safety, especially in unfavorable
environments such as night and rain. However, the current daytime-trained semantic …

The performance of nighttime semantic segmentation is restricted by the poor illumination
and a lack of pixel-wise annotation, which severely limit its application in autonomous …

Most nighttime semantic segmentation studies are based on domain adaptation approaches
and image input. However, limited by the low dynamic range of conventional cameras …

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 …

Generalizing models trained on normal visual conditions to target domains under adverse
conditions is demanding in the practical systems. One prevalent solution is to bridge the …

The majority of learning-based semantic segmentation methods are optimized for daytime
scenarios and favorable lighting conditions. Real-world driving scenarios, however, entail …