A UDA method for semantic segmentation that augments adversarial self-teaching with region growing and class-frequency weighting, with moderate gains over older baselines.
Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation
A UDA method for semantic segmentation that augments adversarial self-teaching with region growing and class-frequency weighting, with moderate gains over older baselines.