IELDG uses inverse evolution layers in both a diffusion data generator and a Mask2Former decoder, plus a frequency fusion module, reporting modest DGSS mIoU gains that are weakened by test-set hyperparameter tuning.
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
REJECT 1representative citing papers
citing papers explorer
-
IELDG: Suppressing Domain-Specific Noise with Inverse Evolution Layers for Domain Generalized Semantic Segmentation
IELDG uses inverse evolution layers in both a diffusion data generator and a Mask2Former decoder, plus a frequency fusion module, reporting modest DGSS mIoU gains that are weakened by test-set hyperparameter tuning.