A 9-parameter calibrated Laplace mixture that models coarse-assignment failures as a heavy tail improves downstream geometric estimation when used as soft weights in a posterior refit.
Netvlad: CNN architecture for weakly supervised place recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semi-Dense Matching Uncertainty Is Not Just Local Confidence
A 9-parameter calibrated Laplace mixture that models coarse-assignment failures as a heavy tail improves downstream geometric estimation when used as soft weights in a posterior refit.