Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation. (arXiv:2207.10892v1 [cs.CV])

We present a novel unsupervised domain adaptation method for semantic
segmentation that generalizes a model trained with source images and
corresponding ground-truth labels to a target domain. A key to domain adaptive
semantic segmentation is to learn domain-invariant and discriminative features
without target ground-truth labels. To this end, we propose a bi-directional
pixel-prototype contrastive learning framework that minimizes intra-class
variations of features for the same object class, while maximizing inter-class
variations for different ones, regardless of domains. Specifically, our
framework …

arxiv bi cv learning segmentation semantic