A multi-level diversification wrapper for test-time adaptation that treats entropy minimization as multi-hypothesis inference to reduce underspecification and improve robustness by 1-4%.
[32] trained a collection of models andidentifiedonlyoneforinference,whichdiscoveredpredictivepatternsnormally missed by a learning algorithm because of the simplicity bias
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification
A multi-level diversification wrapper for test-time adaptation that treats entropy minimization as multi-hypothesis inference to reduce underspecification and improve robustness by 1-4%.