A Stable Diffusion and SAM pipeline generates masked cutouts for novel classes, and mixing them into synthetic source images lets UDA segmentation models learn those classes without modifying the simulator or algorithm.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Class Generation to Expand Semantic Segmentation Datasets
A Stable Diffusion and SAM pipeline generates masked cutouts for novel classes, and mixing them into synthetic source images lets UDA segmentation models learn those classes without modifying the simulator or algorithm.