Systematic multi-variable experiments show panoptic segmentation yields poorer uncertainty quality than semantic, with high variance across datasets and backbones, limited value from time-series samples, calibration gains from sample diversity, and conditional benefits from ensembles over single det
Where are we with calibration under dataset shift in image classification?Transactions on Machine Learn- ing Research, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
U-SEG: Uncertainty in SEGmentation -- A systematic multi-variable exploration
Systematic multi-variable experiments show panoptic segmentation yields poorer uncertainty quality than semantic, with high variance across datasets and backbones, limited value from time-series samples, calibration gains from sample diversity, and conditional benefits from ensembles over single det