Scale variance minimization for unsupervised domain adaptation in image segmentation

• Main Authors: Guan, Dayan, Huang, Jiaxing, Lu, Shijian, Xiao, Aoran
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Unsupervised Domain Adaptation; Image Segmentation
• Online Access: https://hdl.handle.net/10356/157050
• Institution: Nanyang Technological University

We focus on unsupervised domain adaptation (UDA) in image segmentation. Existing works address this challenge largely by aligning inter-domain representations, which may lead over-alignment that impairs the semantic structures of images and further target-domain segmentation performance. We design a...