Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation. (arXiv:2303.05194v2 [cs.CV] UPDATED)

Standard unsupervised domain adaptation methods adapt models from a source to
a target domain using labeled source data and unlabeled target data jointly. In
model adaptation, on the other hand, access to the labeled source data is
prohibited, i.e., only the source-trained model and unlabeled target data are
available. We investigate normal-to-adverse condition model adaptation for
semantic segmentation, whereby image-level correspondences are available in the
target domain. The target set consists of unlabeled pairs of adverse- and
normal-condition street images …

arxiv contrastive model data domain adaptation robustness segmentation semantic source data standard unsupervised