DA-VSN is a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos . The network is based on cross-domain TCR that guides the prediction of target frames to have similar temporal consistency as that of source frames (learnt from annotated source data) viaadversarial learning . Extensive experiments demonstrate the superiority of our proposed network which outperformsmultiple baselines consistently by large margins . The proposed network outperforms the baselines of other networks by large margin by large amounts of time . It is based at the University of Cambridge, England, on the basis of previous studies .

Author(s) : Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu

Links : PDF - Abstract

Code :
Coursera

Keywords : domain - network - temporal - frames - consistency -

Leave a Reply

Your email address will not be published. Required fields are marked *