NEO performs test-time adaptation by re-centering target latent embeddings at the origin, boosting accuracy on distribution-shifted datasets like ImageNet-C with no optimization or hyperparameters and minimal extra compute.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Multi-purposing the domain discriminator to supply both domain-invariance and pseudo-label confidence scores in domain adaptation.
citing papers explorer
-
NEO: No-Optimization Test-Time Adaptation through Latent Re-Centering
NEO performs test-time adaptation by re-centering target latent embeddings at the origin, boosting accuracy on distribution-shifted datasets like ImageNet-C with no optimization or hyperparameters and minimal extra compute.
-
Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence
Multi-purposing the domain discriminator to supply both domain-invariance and pseudo-label confidence scores in domain adaptation.