Context-Aware Mixup for Domain Adaptive Semantic Segmentation

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 2; pp. 804 - 817
• Main Authors: Zhou, Qianyu, Feng, Zhengyang, Gu, Qiqi, Pang, Jiangmiao, Cheng, Guangliang, Lu, Xuequan, Shi, Jianping, Ma, Lizhuang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; autonomous driving; Context; Degradation; Domain adaptation; domain mixup; Domains; Electronic mail; Image segmentation; Performance degradation; scene understanding; Semantic segmentation; Semantics; Spatial distribution; Task analysis; Uncertainty

Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Existing UDA-based semantic segmentation approaches always reduce the domain shifts in pixel level, feature level, and output level. However, almost all of them largely neglect the...