AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation. (arXiv:2107.10140v2 [cs.CV] UPDATED)

Most modern approaches for domain adaptive semantic segmentation rely on
continued access to source data during adaptation, which may be infeasible due
to computational or privacy constraints. We focus on source-free domain
adaptation for semantic segmentation, wherein a source model must adapt itself
to a new target domain given only unlabeled target data. We propose
Augmentation Consistency-guided Self-training (AUGCO), a source-free adaptation
algorithm that uses the model's pixel-level predictive consistency across
diverse, automatically generated views of each target image along …

arxiv augmentation cv segmentation semantic training