Aligning the covariance of test features to the covariance of the most confident test predictions improves test-time adaptation accuracy at a fraction of the usual compute cost.
Towards real-world test-time adaptation: Tri-net self-training with balanced normaliza- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Test-time Correlation Alignment
Aligning the covariance of test features to the covariance of the most confident test predictions improves test-time adaptation accuracy at a fraction of the usual compute cost.