DART improves test-time adaptation under label distribution shift by learning, from training batches with simulated class imbalance, an affine correction to the classifier's logits.
Adapting visual category models to new domains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation
DART improves test-time adaptation under label distribution shift by learning, from training batches with simulated class imbalance, an affine correction to the classifier's logits.