NAVIA augments the [CLS] token with adaptive biases in shallow ViT layers so entropy-minimizing test-time adaptation can recover information lost to token aggregation, reporting over 2.5% accuracy gains and over 20% latency reduction.
Parameter-free online test-time adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation
NAVIA augments the [CLS] token with adaptive biases in shallow ViT layers so entropy-minimizing test-time adaptation can recover information lost to token aggregation, reporting over 2.5% accuracy gains and over 20% latency reduction.