“…Unsupervised domain adaptation (UDA) [3,4,5,12,13,14,15,16,17,18,19,20,21,22,23,24] aims to adapt the model trained on a labeled source domain to an unlabeled target domain when there is distinct domain divergence. A series of UDA algorithms [25,26,27,28,29,30,31] have been proposed by employing an adversarial learning strategy where the semantic features of the source and target data are aligned for reducing domain divergence.…”