Temporal Consistency as Pretext Task in Unsupervised Domain Adaptation for Semantic Segmentation

• Published in: Journal of intelligent & robotic systems Vol. 111; no. 1; p. 37
• Main Authors: Barbosa, Felipe, Osório, Fernando
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 19.03.2025; Springer Nature B.V
• Subjects: Adaptation; Artificial Intelligence; Computer vision; Control; Deep learning; Electrical Engineering; Engineering; Image segmentation; Mechanical Engineering; Mechatronics; Object recognition; Obstacle avoidance; Regular Paper; Robotics; Self-supervised learning; Semantic segmentation; Semantics; Unsupervised learning; Video data; Vision systems; Unsupervised domain adaptation; Temporal consistency; Review; Semantic segmentation; Self-supervised learning

Intelligent and autonomous robots (and vehicles) largely adopt computer vision systems to help in localization, navigation and obstacle avoidance tasks. By integrating different deep learning techniques, such as Object Detection and Image Semantic Segmentation, these systems achieve high accuracy in...