A GAN generates synthetic built-up pixels that, when added to a tiny training set, raise an ANN classifier's accuracy and kappa on Landsat7 imagery.
The fundamental problems that these models try to solve are, (i) to estimate the underlying distribution of the observed data and (ii) to generate sample data from the same
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Application of Generative Adversarial Network (GAN) for Synthetic Training Data Creation to improve performance of ANN Classifier for extracting Built-Up pixels from Landsat Satellite Imagery
A GAN generates synthetic built-up pixels that, when added to a tiny training set, raise an ANN classifier's accuracy and kappa on Landsat7 imagery.