Cycle-consistent translation between images and segmentation masks acts as an unsupervised regularizer and improves low-label semi-supervised segmentation on some benchmarks, though the reported gains are dataset-dependent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting CycleGAN for semi-supervised segmentation
Cycle-consistent translation between images and segmentation masks acts as an unsupervised regularizer and improves low-label semi-supervised segmentation on some benchmarks, though the reported gains are dataset-dependent.