A semi-supervised semantic segmentation method combining aleatoric uncertainty loss and energy-based loss with union-intersection pseudo-labels gives modest gains over the CPCL baseline on PASCAL VOC and Cityscapes, but not state-of-the-art results.
Uncertainty esti- mation based adversarial attack in multi-class classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation
A semi-supervised semantic segmentation method combining aleatoric uncertainty loss and energy-based loss with union-intersection pseudo-labels gives modest gains over the CPCL baseline on PASCAL VOC and Cityscapes, but not state-of-the-art results.