Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation. (arXiv:2205.11192v2 [cs.CV] UPDATED)

To further reduce the cost of semi-supervised domain adaptation (SSDA)
labeling, a more effective way is to use active learning (AL) to annotate a
selected subset with specific properties. However, domain adaptation tasks are
always addressed in two interactive aspects: domain transfer and the
enhancement of discrimination, which requires the selected data to be both
uncertain under the model and diverse in feature space. Contrary to active
learning in classification tasks, it is usually challenging to select pixels
that contain …

arxiv cv domain adaptation segmentation semantic