A deep network trained with a transformation-consistency loss and a spatial memory map can correct per-instance geometric annotation noise, matching or beating supervised baselines on satellite imagery.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations
A deep network trained with a transformation-consistency loss and a spatial memory map can correct per-instance geometric annotation noise, matching or beating supervised baselines on satellite imagery.