A source-free domain adaptation method combining evidential deep learning with a per-dataset tuned calibrated softmax improves Domainnet40 and Office-Home slightly, but reduces average accuracy on Office31.
Dirichlet-based prediction calibra- tion for learning with noisy labels
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
-
Label Calibration in Source Free Domain Adaptation
A source-free domain adaptation method combining evidential deep learning with a per-dataset tuned calibrated softmax improves Domainnet40 and Office-Home slightly, but reduces average accuracy on Office31.