A combination of consistency regularization, pixel contrastive learning, and self-training achieves near-supervised semantic segmentation in semi-supervised domain adaptation with as few as 50 target labels.
Semi-supervised semantic segmentation with pixel-level contrastive learning from a class-wise memory bank
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Last Mile to Supervised Performance: Semi-Supervised Domain Adaptation for Semantic Segmentation
A combination of consistency regularization, pixel contrastive learning, and self-training achieves near-supervised semantic segmentation in semi-supervised domain adaptation with as few as 50 target labels.