A Data-Centric Approach for Rapid Dataset Generation Using Iterative Learning and Sparse Annotations

Abstract

This study investigates the application of iterative sparse annotations for semantic segmentation in remote-sensing imagery, focusing on minimizing the laborious and expensive data labeling process. By leveraging Geographic Information Systems (GIS), we implemented circular polygon shapefiles to label portions of each class, attributing a value of -1 outside these polygons. The model training used the simplified BSB Aerial Dataset with eight classes. The semantic segmentation model was U-Net architecture with the Efficient-net-B7 backbone and a modified cross-entropy loss function. Our results showed promising improvement, particularly in error-prone classes, with the iterative addition of more samples. This approach suggests a quicker method for dataset creation using sparse, iteratively enhanced annotations. Future work will aim to implement further iterative rounds to approximate the results of continuous labeling, thereby enhancing the efficiency of semantic segmentation in large-scale remote-sensing images.