CVNov 6, 2017

Artificial Generation of Big Data for Improving Image Classification: A Generative Adversarial Network Approach on SAR Data

arXiv:1711.02010v17 citations
Originality Synthesis-oriented
AI Analysis

This work addresses a data scarcity problem in remote sensing for urban and periurban areas, but it appears incremental as it applies existing GAN methods to SAR data.

The authors tackled the lack of large-scale SAR image datasets by proposing a new dataset and using it to explore patch-based classification with 7 semantic classes, and they found that synthetic data generated by a GAN can improve classification accuracy, though no specific numbers are provided.

Very High Spatial Resolution (VHSR) large-scale SAR image databases are still an unresolved issue in the Remote Sensing field. In this work, we propose such a dataset and use it to explore patch-based classification in urban and periurban areas, considering 7 distinct semantic classes. In this context, we investigate the accuracy of large CNN classification models and pre-trained networks for SAR imaging systems. Furthermore, we propose a Generative Adversarial Network (GAN) for SAR image generation and test, whether the synthetic data can actually improve classification accuracy.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes