Collection of real world annotations for training semantic segmentation models is an expensive process. Unsupervised domain adaptation (UDA) tries to solve this problem by studying how more accessible data such as synthetic can be used train and adapt images without requiring their annotations. Recent UDA methods applies self-learning on pixel-wise classification loss using a student teacher ne...

Distributed preference relation (DPR) is a way to simultaneously characterize the preferred, nonpreferred, indifferent, and global ignorance degrees of one alternative over another. To make DPRs applicable in decision-making, consistency addressed this paper. Under assumption that any two on set alternatives are independent each other, four rules regarding relationship between designed develop ...