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.
128 512 2048 8192 32768 Number of Samples 37.5 40.0 42.5 45.0 47.5 50.0 52.5 55.0 57.5Average Accuracy No Adapt T3A SAR LAME TENT CoTTA FOA Surgeon NEO NEO Cont
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
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.