ADAPT reframes test-time adaptation as probabilistic Gaussian inference with CLIP-guided regularization, delivering SOTA results without gradients, source data, or full target access in both online and transductive settings.
Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting
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
-
Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
ADAPT reframes test-time adaptation as probabilistic Gaussian inference with CLIP-guided regularization, delivering SOTA results without gradients, source data, or full target access in both online and transductive settings.